© 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. 25-GEMMASCOPE-RES-16K
    11. 792
    Prev
    Next
    INDEX
    Explanations

    issues of governance and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.79
    rungsseite
    -0.78
    RectangleBorder
    -0.70
     Normdatei
    -0.65
    ########.
    -0.60
     newBuilder
    -0.57
     الرياضيه
    -0.57
     تضيفلها
    -0.55
     BioLib
    -0.55
    EndInit
    -0.54
    POSITIVE LOGITS
    WithMany
    0.48
     fok
    0.45
     múl
    0.45
     Accounts
    0.45
     évit
    0.44
     év
    0.44
    ESTON
    0.43
    তথ্যসূত্র
    0.43
    addPreferredGap
    0.42
    seende
    0.41
    Activations Density 0.121%

    No Known Activations