© 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. 15-GEMMASCOPE-RES-16K
    6. 2027
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data manipulation and file processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.82
    sizeCache
    -0.79
    ConstraintMaker
    -0.61
    fillType
    -0.59
    MessageOf
    -0.55
    vician
    -0.55
    DoubleQuotes
    -0.51
    aarrggbb
    -0.51
    ngilizce
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    POSITIVE LOGITS
     ulang
    0.68
     proprement
    0.65
     themselves
    0.65
    themselves
    0.61
     démarrage
    0.59
    RTSC
    0.58
     rzeczy
    0.58
    LEGGI
    0.57
     precisione
    0.55
    เอง
    0.55
    Activations Density 0.549%

    No Known Activations