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. 20-GEMMASCOPE-RES-16K
    6. 11860
    Prev
    Next
    INDEX
    Explanations

    references to bands or groups, particularly in the context of music or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "band" and its context

    np_acts-logits-general · gemini-2.0-flash

    band

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Collectors
    -0.67
    ̷
    -0.55
    ATUR
    -0.53
     Dilemma
    -0.53
    prüfung
    -0.52
    ')}}
    -0.51
    utors
    -0.50
     Frö
    -0.50
     Disclosure
    -0.49
     tè
    -0.49
    POSITIVE LOGITS
     bands
    1.33
     Bands
    1.23
     BAND
    1.21
    Band
    1.17
     Band
    1.15
     band
    1.14
    Bands
    1.13
    bands
    1.06
    icoot
    1.04
    band
    1.03
    Activations Density 0.080%

    No Known Activations