© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4063
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instructions and outputs for symbolic algebra problems—particularly “Solve/Simplify/Let” directives, “for” clauses, and power/exponent notation in math expressions.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    mathematical problem-solving language.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    mathematical expressions, equations, and operations involving variables and numerical notation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    věd
    -0.45
     track
    -0.45
    ControllerTest
    -0.43
    même
    -0.42
    免
    -0.40
     meia
    -0.39
     Hyde
    -0.39
     quick
    -0.39
    midler
    -0.38
    oubliez
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    1.03
    aarrggbb
    0.91
    contentLoaded
    0.84
     تضيفلها
    0.82
    Datuak
    0.81
     ModelExpression
    0.79
    SharedDtor
    0.78
    StructEnd
    0.77
    Xna
    0.76
    évaluateur
    0.74
    Activations Density 1.049%

    No Known Activations