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. 34-GEMMASCOPE-RES-16K
    6. 10821
    Prev
    Next
    INDEX
    Explanations

    information related to submissions, forms, and event participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.40
    раздо
    -0.38
    喱
    -0.35
    🦵
    -0.30
     Pourtant
    -0.29
    */].
    -0.29
     Infatti
    -0.28
    >{@
    -0.28
    ">—
    -0.26
     przecież
    -0.26
    POSITIVE LOGITS
     please
    1.01
     Please
    0.91
    Please
    0.87
     refunds
    0.81
     anyone
    0.81
    please
    0.79
     Anyone
    0.79
     Individuals
    0.77
     PLEASE
    0.77
     additional
    0.74
    Activations Density 0.375%

    No Known Activations