© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5995
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific identifiers in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hırka
    -0.40
     küpe
    -0.40
     bileklik
    -0.34
     eşofman
    -0.34
    Portail
    -0.33
    fael
    -0.33
     gynhyrchwyd
    -0.33
     desenli
    -0.33
     hoş
    -0.33
     esternos
    -0.33
    POSITIVE LOGITS
     Y
    2.63
     y
    2.25
    Y
    2.09
     getY
    1.91
    getY
    1.73
     YE
    1.71
     YC
    1.69
    Y
    1.59
     YS
    1.59
     Yo
    1.59
    Activations Density 4.464%

    No Known Activations