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. 985
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions and criteria

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

    the word "condition" appearing in technical, legal, scientific, or formal contexts.

    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
     juguete
    -0.42
     PARSER
    -0.40
     burbujas
    -0.39
    setVerticalGroup
    -0.38
    +#+
    -0.38
     ejer
    -0.38
     toalla
    -0.37
    zenta
    -0.37
    eluarkan
    -0.36
     atve
    -0.36
    POSITIVE LOGITS
     Cond
    0.63
     Condition
    0.62
     Condi
    0.59
     cond
    0.59
    Condi
    0.59
     Conditions
    0.56
    condi
    0.56
    Condition
    0.56
    Cond
    0.56
    kond
    0.53
    Activations Density 0.223%

    No Known Activations