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. 24-GEMMASCOPE-RES-16K
    6. 2421
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terminology and court procedures

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

    "other" or "all" as a determiner

    np_acts-logits-general · gemini-2.0-flash

    all other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.55
     <=",
    -0.55
    ❉
    -0.54
    netbeans
    -0.52
    addPreferredGap
    -0.49
    setViewName
    -0.49
    Cyfeiriadau
    -0.48
    UserScript
    -0.47
    Jîn
    -0.46
    pezi
    -0.46
    POSITIVE LOGITS
     other
    4.19
    other
    3.57
     others
    3.33
    autres
    3.16
    Other
    3.13
     otros
    3.09
     Other
    3.05
    others
    3.04
     autres
    3.03
     otras
    2.93
    Activations Density 2.360%

    No Known Activations