© 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. 12-GEMMASCOPE-RES-16K
    6. 6743
    Prev
    Next
    INDEX
    Explanations

    key concepts related to relationships, connections, and dependencies in various contexts

    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
    AntiForgeryToken
    -0.70
    الحياه
    -0.66
    ırlı
    -0.57
    PreExecute
    -0.55
    labelledby
    -0.55
    Revenir
    -0.54
     viewDidLoad
    -0.53
     виправивши
    -0.53
    تقاوى
    -0.52
    FromJson
    -0.52
    POSITIVE LOGITS
     into
    0.65
     kepada
    0.64
    égard
    0.61
     dekat
    0.56
    กับ
    0.54
    ">—
    0.54
     with
    0.53
     toward
    0.52
     INTO
    0.51
     closer
    0.51
    Activations Density 0.689%

    No Known Activations