© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10828
    Prev
    Next
    INDEX
    Explanations

    URLs and path-like structures 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 @ 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
     Roskov
    -0.72
    WarningLevel
    -0.56
     SwitchCompat
    -0.53
    LookAnd
    -0.49
    AsUp
    -0.49
    ThroughAttribute
    -0.48
    LayoutStyle
    -0.45
     Smithsonian
    -0.45
    oneofs
    -0.44
    Accessors
    -0.43
    POSITIVE LOGITS
    ('/
    1.06
    (['/
    0.96
    :'/
    0.95
    (`/
    0.95
    PostMapping
    0.94
     imageNamed
    0.93
    ={`/
    0.93
    ="/
    0.90
     /\.
    0.88
    ='/
    0.86
    Activations Density 0.042%

    No Known Activations