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. 15070
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental protocols and methods in scientific research

    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
    EXP
    -0.50
    Extr
    -0.50
     Involved
    -0.49
    Ida
    -0.49
    ANIM
    -0.48
    INFORMATION
    -0.48
    Apr
    -0.48
    Exposition
    -0.47
    Ita
    -0.47
    Iron
    -0.47
    POSITIVE LOGITS
    épaisseur
    0.88
    enfance
    0.83
     ін
    0.83
     イン
    0.79
    イン
    0.79
     ин
    0.75
     mengin
    0.75
    hygiène
    0.75
    amitié
    0.71
    échelle
    0.70
    Activations Density 1.947%

    No Known Activations