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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 416
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and operations related to calculations and evaluations

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

    mathematical expressions and arithmetic operations in word problems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Afterward
    -0.47
     dramatically
    -0.46
     envisioned
    -0.45
     Großen
    -0.44
    nullptr
    -0.43
     referenced
    -0.43
     pictured
    -0.42
     Straß
    -0.41
     nighttime
    -0.41
     oftentimes
    -0.40
    POSITIVE LOGITS
     upto
    0.69
    upto
    0.65
    __":
    
    0.59
    ՚
    0.58
    Contd
    0.57
     :-
    0.57
     NCERT
    0.56
     Colour
    0.55
     kms
    0.54
     wastage
    0.54
    Activations Density 0.413%

    No Known Activations