© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    occurrences of the file type "png" in the text

    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
    AnchorStyles
    -0.61
     Chwiliwch
    -0.57
    ########.
    -0.56
    hom
    -0.54
     protoimpl
    -0.53
    gand
    -0.51
    QMetaType
    -0.51
    Compar
    -0.51
    HideFlags
    -0.51
     coag
    -0.51
    POSITIVE LOGITS
     judiciaire
    0.63
     scientifiques
    0.61
     extérieures
    0.60
    SequentialGroup
    0.60
     fiscale
    0.60
     financières
    0.59
     médicaux
    0.59
     supposing
    0.58
     חיצוניים
    0.58
    rungsseite
    0.57
    Activations Density 0.086%

    No Known Activations