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. 18-GEMMASCOPE-RES-16K
    6. 998
    Prev
    Next
    INDEX
    Explanations

    references to "band" in various contexts

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

    The token "Band" and its variations

    np_acts-logits-general · gemini-2.0-flash

    band with names or job levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̷
    -0.58
     McGuire
    -0.57
    ATUR
    -0.53
    Collectors
    -0.52
    dient
    -0.50
     truc
    -0.50
     tasca
    -0.50
     verg
    -0.49
     custo
    -0.49
     Subject
    -0.48
    POSITIVE LOGITS
     bands
    1.66
     BAND
    1.59
     Bands
    1.54
     band
    1.52
    Band
    1.51
     Band
    1.50
    Bands
    1.44
     banded
    1.38
    BAND
    1.36
     banding
    1.33
    Activations Density 0.124%

    No Known Activations