© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 46829
    Prev
    Next
    INDEX
    Explanations

    references to publications and associated metadata

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

    book titles and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.44
     rekening
    -0.37
    PyExc
    -0.35
    MENAFN
    -0.34
     altogether
    -0.34
    Diwedd
    -0.33
    Looper
    -0.33
     Sumatra
    -0.33
     clover
    -0.32
    RectangleBorder
    -0.32
    POSITIVE LOGITS
     ब्रेकडाउन
    0.55
    ValueStyle
    0.49
    ffè
    0.47
    RegistryLite
    0.44
    CppMethod
    0.43
     Bow
    0.41
    bootstrapcdn
    0.40
     Injector
    0.40
    FunctionFlags
    0.40
     CanadaChoose
    0.39
    Activations Density 0.016%

    No Known Activations