© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    references to sewing supplies and materials

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

    following "in", "on", "from" related to keeping things

    np_acts-logits-general · gemini-2.0-flash

    storing things

    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
    findpost
    -0.59
    queryInterface
    -0.57
    makeConstraints
    -0.52
     esboço
    -0.47
    новниш
    -0.47
    PhysRevLett
    -0.47
    bleed
    -0.45
    ruptedException
    -0.45
    :+:
    -0.43
    nytt
    -0.43
    POSITIVE LOGITS
     storage
    1.65
     stored
    1.64
     storing
    1.49
    storage
    1.39
     Storage
    1.38
    stored
    1.35
     STORAGE
    1.32
     Stored
    1.29
    Storage
    1.27
    Stored
    1.23
    Activations Density 0.315%

    No Known Activations