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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 8246
    Prev
    Next
    INDEX
    Explanations

    technical or procedural jargon and references

    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
     صوتيه
    -0.67
     kiệm
    -0.48
    pagation
    -0.46
    Biografía
    -0.45
     تضيفلها
    -0.45
     الحره
    -0.44
    drawal
    -0.44
    NUMX
    -0.44
     multil
    -0.43
    匿名使用者
    -0.43
    POSITIVE LOGITS
    keits
    0.36
    ời
    0.36
    Referencies
    0.35
    wpi
    0.34
     متعلقه
    0.33
    sieht
    0.32
    LookAnd
    0.32
    gefü
    0.32
     kazan
    0.32
    ApiRequest
    0.31
    Activations Density 0.117%

    No Known Activations