Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3076
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to transmission processes and coding in systems

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

    mathematical notation and symbols in technical/scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words that indicate simultaneous or sequential actions happening together.

    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
     resourceCulture
    -0.82
    httphttps
    -0.76
    AndEndTag
    -0.75
     незавершена
    -0.66
    IntoConstraints
    -0.63
     Subtraction
    -0.60
    nodoc
    -0.58
     Minus
    -0.57
     يتيمه
    -0.57
     yyb
    -0.56
    POSITIVE LOGITS
     positivos
    0.63
     positivas
    0.58
     positive
    0.55
     justru
    0.55
     positivo
    0.54
     juist
    0.52
     positiva
    0.52
     positif
    0.47
     dương
    0.46
     affirmative
    0.46
    Activations Density 1.217%

    No Known Activations