© 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. 11056
    Prev
    Next
    INDEX
    Explanations

    the structure and format of narrative forms, especially in writing

    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
    DllImport
    -0.77
     <<<<<<<<<<<<<<
    -0.72
    MessageTagHelper
    -0.65
    AddTagHelper
    -0.62
     Plates
    -0.62
     وتسجيلات
    -0.60
    ActionCreators
    -0.58
     snee
    -0.56
    OGND
    -0.55
     Plate
    -0.55
    POSITIVE LOGITS
     format
    0.68
     bentuk
    0.66
     style
    0.63
     type
    0.61
    形式
    0.57
    RunWith
    0.57
     shape
    0.56
     formato
    0.56
     modalidad
    0.56
     berbentuk
    0.56
    Activations Density 0.614%

    No Known Activations