© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8526
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly related to functions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighton
    -0.45
    ัด
    -0.42
     Aub
    -0.41
    мед
    -0.41
     rec
    -0.41
     L
    -0.39
     tot
    -0.39
    hideLoading
    -0.39
    ลิ
    -0.39
    Titre
    -0.39
    POSITIVE LOGITS
     للمعارف
    1.06
     متعلقه
    1.02
    sizeCache
    0.93
     >=",
    0.93
     <<<<<<<<<<<<<<
    0.93
    awtextra
    0.92
    __(/*!
    0.90
    Portail
    0.84
    Obrázky
    0.84
     onPostExecute
    0.84
    Activations Density 0.173%

    No Known Activations