Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1772
    Prev
    Next
    INDEX
    Explanations

    information related to high-ranking athletes and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.69
    >>()
    -0.59
     obec
    -0.59
    expandindo
    -0.59
    DockStyle
    -0.58
    </caption>
    -0.56
    िखित
    -0.56
    }))
    
    -0.56
     Cæsar
    -0.56
    AIDS
    -0.55
    POSITIVE LOGITS
    setVerticalGroup
    0.51
     كرة
    0.49
     freshman
    0.47
    varlak
    0.47
     aren
    0.47
    ffel
    0.46
    utella
    0.46
     autorytatywna
    0.45
    illac
    0.44
    rende
    0.44
    Activations Density 0.125%

    No Known Activations