© 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. 8-GEMMASCOPE-RES-16K
    6. 4425
    Prev
    Next
    INDEX
    Explanations

    references to conferences

    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
     utilis
    -0.73
     Vitro
    -0.73
    disposed
    -0.72
     Jail
    -0.70
     Betis
    -0.70
    kad
    -0.69
     ActionResult
    -0.68
    __*/
    -0.66
    Guil
    -0.66
     numberWith
    -0.65
    POSITIVE LOGITS
     conferences
    1.71
     conference
    1.65
     Conference
    1.59
     Conferences
    1.58
    Conference
    1.47
     CONFERENCE
    1.38
    conference
    1.35
     Conférence
    1.17
    konferenz
    1.17
     Konferenz
    1.16
    Activations Density 0.067%

    No Known Activations