© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 922
    Prev
    Next
    INDEX
    Explanations

    terms that indicate quality and assessment

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    is followed by adjectives/adverbs

    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
    ViewImports
    -0.59
     quei
    -0.56
     eint
    -0.55
    ambilan
    -0.53
     kehilangan
    -0.52
    livé
    -0.52
     Hongrie
    -0.50
    rpn
    -0.50
    Incoming
    -0.49
    unsqueeze
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.78
    numerusform
    0.65
    ...');
    0.65
     Numerade
    0.65
    ...");
    0.64
    "],
    0.61
    "},
    0.61
    GraphicsUnit
    0.60
    "),
    0.60
     тоже
    0.60
    Activations Density 0.397%

    No Known Activations