© 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. 7-GEMMASCOPE-RES-16K
    6. 4206
    Prev
    Next
    INDEX
    Explanations

    terms related to sponsorship and funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gell
    -0.63
    gång
    -0.59
    Joh
    -0.59
     مشين
    -0.57
    v
    -0.56
    TEMPO
    -0.56
     ActionResult
    -0.56
    jell
    -0.56
     Tep
    -0.55
     Bernardino
    -0.55
    POSITIVE LOGITS
     sponsors
    2.22
     sponsor
    2.12
     Sponsors
    2.05
     sponsorship
    2.00
     Sponsor
    1.96
     sponsored
    1.94
     sponsoring
    1.89
    Sponsors
    1.87
    Sponsor
    1.86
     SPONS
    1.78
    Activations Density 0.096%

    No Known Activations