© 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. 3811
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or variables represented by "Y"

    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
     createSlice
    -0.74
    UIControlState
    -0.73
     المعيارى
    -0.73
    "");
    -0.73
    Personensuche
    -0.73
    صه
    -0.72
    StructEnd
    -0.72
    ladimir
    -0.67
    lső
    -0.66
    veral
    -0.65
    POSITIVE LOGITS
     getY
    1.23
     Yates
    1.13
     Y
    1.12
     Yel
    1.10
     Yag
    1.07
     Yaz
    1.05
    Yves
    1.05
     Yard
    1.04
     Yves
    1.04
    yAxis
    1.03
    Activations Density 0.322%

    No Known Activations