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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7115
    Prev
    Next
    INDEX
    Explanations

    references to regulatory agencies or commissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    specifier
    -0.55
     Heb
    -0.53
    ScopeManager
    -0.53
    rinha
    -0.51
    órias
    -0.51
    шити
    -0.50
     Enero
    -0.50
    ுகள்
    -0.49
    #+#
    -0.49
     cesta
    -0.48
    POSITIVE LOGITS
     Commission
    0.77
    qrstuvwxyz
    0.73
    Commission
    0.73
    原始内容存档于
    0.72
     Commissions
    0.70
     mL
    0.68
    __":
    0.64
     commissioners
    0.64
     afield
    0.63
    CGRectMake
    0.63
    Activations Density 0.221%

    No Known Activations