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. 15680
    Prev
    Next
    INDEX
    Explanations

    elements related to requirements and conditions in contexts like legal or procedural discussions

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

    Following "been," "is," "be," or "was."

    np_acts-logits-general · gemini-2.0-flash

    conditions met or achieved

    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
     Paglinawan
    -0.64
    UrlResolution
    -0.64
    WebElementEntity
    -0.63
     calculées
    -0.61
    évaluateur
    -0.59
     lenker
    -0.56
     متعلقه
    -0.55
    expandindo
    -0.55
    Datuak
    -0.54
     igång
    -0.54
    POSITIVE LOGITS
     overcome
    0.85
     conquered
    0.80
     conquer
    0.74
     exceeded
    0.71
     surpassed
    0.71
     crossed
    0.67
     reached
    0.65
    CrossRef
    0.64
     avoided
    0.64
     traversed
    0.63
    Activations Density 0.353%

    No Known Activations