© 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. 9-GEMMASCOPE-RES-16K
    11. 1167
    Prev
    Next
    INDEX
    Explanations

    document structure or formatting indicators, such as section headers or formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.88
     nahilalakip
    -0.87
    ]='\
    -0.83
     utafitiHapana
    -0.82
     fhould
    -0.82
    ">—
    -0.81
    HasBeenSet
    -0.81
    ſelves
    -0.81
    GIVEREF
    -0.79
    scriptId
    -0.78
    POSITIVE LOGITS
    reactstrap
    0.49
    \{\\
    0.49
    -
    0.48
    ,
    0.48
    '
    0.47
     hilarious
    0.47
    //
    0.46
     st
    0.46
    0.44
    L
    0.44
    Activations Density 0.018%
    No Known Activations