Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2783
    Prev
    Next
    INDEX
    Explanations

    expressions of enthusiasm and affection towards the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meanwhile
    -0.46
     meanwhile
    -0.44
    TouchEvent
    -0.41
    Meanwhile
    -0.41
    Furthermore
    -0.40
    /
    -0.37
    con
    -0.37
    PerformLayout
    -0.36
     asimismo
    -0.36
    fill
    -0.36
    POSITIVE LOGITS
    WebElementEntity
    0.88
    ftagPool
    0.82
    GraphicsUnit
    0.81
    expandindo
    0.81
     >=",
    0.78
    awtextra
    0.78
     <>",
    0.76
     beginnetje
    0.75
    StoreMessageInfo
    0.74
    Portale
    0.73
    Activations Density 0.328%

    No Known Activations