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. 38-GEMMASCOPE-RES-16K
    6. 15027
    Prev
    Next
    INDEX
    Explanations

    references to requirements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.57
    DataPropertyName
    -0.39
     andererseits
    -0.38
    ですし
    -0.38
    ViewImports
    -0.37
     مؤرشف
    -0.36
    oader
    -0.35
    ItemBackground
    -0.35
    $_['
    -0.35
    évaluateur
    -0.35
    POSITIVE LOGITS
     following
    3.89
    following
    3.39
     Following
    2.98
    Following
    2.95
     FOLLOWING
    2.89
     siguientes
    2.63
     seguinte
    2.58
     folgende
    2.55
     folgenden
    2.50
     siguiente
    2.47
    Activations Density 1.637%

    No Known Activations