© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12549
    Prev
    Next
    INDEX
    Explanations

    quotation marks and their surrounding context in the text

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

    preceding verbs like "make", "look", "cook", or "open"

    np_acts-logits-general · gemini-2.0-flash

    verbs in quotes

    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
    marginHorizontal
    -0.61
    konomi
    -0.59
    plaatst
    -0.59
    asString
    -0.55
    loggedIn
    -0.53
    ongen
    -0.53
     Bearbeitung
    -0.53
     obstructed
    -0.52
    kregen
    -0.52
    currentItem
    -0.52
    POSITIVE LOGITS
    take
    0.92
    make
    0.88
    go
    0.83
    have
    0.82
    give
    0.81
    get
    0.80
    testify
    0.73
    hold
    0.73
    bring
    0.73
    look
    0.73
    Activations Density 0.218%

    No Known Activations