© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 14664
    Prev
    Next
    INDEX
    Explanations

    the presence of markup or structured formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.57
     collègues
    -0.54
    UMBIA
    -0.54
    forsk
    -0.53
     natal
    -0.51
     المعيارى
    -0.49
     natale
    -0.47
    __*/
    -0.47
    ajas
    -0.47
     مرئيه
    -0.47
    POSITIVE LOGITS
    getActiveSheet
    0.69
    featureID
    0.69
     ErrIntOverflow
    0.68
    EndGlobalSection
    0.65
    DeleteBehavior
    0.64
    TypedDataSet
    0.63
    SuppressMessage
    0.60
    CreateModel
    0.58
     Италијани
    0.58
    ftagPool
    0.58
    Activations Density 0.060%

    No Known Activations