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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 9116
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terminology related to reporting and documenting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.98
    
    -0.93
    脚注の使い方
    -0.85
     OFDb
    -0.81
    tvguidetime
    -0.75
     calendriers
    -0.72
    setVerticalGroup
    -0.71
    NUMX
    -0.70
    Personendaten
    -0.70
    ArgsConstructor
    -0.67
    POSITIVE LOGITS
     relayed
    0.84
     forwarded
    0.84
     report
    0.81
     relay
    0.78
     send
    0.76
     submit
    0.74
     sent
    0.69
     Report
    0.67
     submitted
    0.65
     transmitted
    0.65
    Activations Density 0.342%

    No Known Activations