Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5378
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to published works or articles

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

    Year after author names in papers

    np_acts-logits-general · gemini-2.0-flash

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     للاسماء
    -0.55
     متعلقه
    -0.54
     '\\;'
    -0.52
    ]")]
    -0.51
    ittarius
    -0.51
    XtraReports
    -0.48
    存于互联网档案馆
    -0.48
    ConstraintMaker
    -0.48
    Архівовано
    -0.48
     استنادى
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.57
     Gilbert
    0.35
     zijne
    0.34
    Personal
    0.33
     instructive
    0.33
    model
    0.32
    ähteet
    0.32
     guantes
    0.32
     Personal
    0.32
     penting
    0.31
    Activations Density 0.315%

    No Known Activations