© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13079
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical expressions used in problem-solving contexts

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

    question prompts and assignment-style instructions in academic or educational contexts

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

    question words and instructional/imperative language used in prompts, assignments, and queries.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102

    questions and instructions.

    oai_token-act-pair · deepseek-r1Triggered 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
    cshtml
    -0.72
     indisponible
    -0.51
     nämlich
    -0.48
    ########.
    -0.47
     رم
    -0.46
     initComponents
    -0.46
     infatti
    -0.44
    Tracce
    -0.44
    \{\\
    -0.44
    XN
    -0.42
    POSITIVE LOGITS
     ſind
    0.74
     становника
    0.65
     ſtate
    0.65
     yourselves
    0.63
     yourself
    0.62
     Polit
    0.60
     myſelf
    0.59
     Roskov
    0.59
     juſ
    0.59
     Presby
    0.58
    Activations Density 0.283%

    No Known Activations