© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7119
    Prev
    Next
    INDEX
    Explanations

    numeric values

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

    The number 1 in various formats

    np_acts-logits-general · gemini-2.0-flash

    numbers and division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.89
    ésultats
    -0.89
    addCriterion
    -0.83
     deſſen
    -0.82
    enablog
    -0.82
    ագրություններ
    -0.82
    arangay
    -0.81
    BibitemShut
    -0.81
    iſchen
    -0.81
    ьаж
    -0.81
    POSITIVE LOGITS
    1
    0.89
    l
    0.42
    1
    0.40
     eleven
    0.35
     Eleventh
    0.35
    १
    0.34
    ১
    0.32
    in
    0.31
    il
    0.30
    I
    0.30
    Activations Density 1.026%

    No Known Activations