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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 42257
    Prev
    Next
    INDEX
    Explanations

    key phrases that indicate actions, outcomes, or relationships in a context involving performance and evaluation

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

    numbers and quantities

    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
    IntoConstraints
    -0.41
    нциклопедия
    -0.38
    InstrumentedTest
    -0.37
    本線
    -0.37
    Opéra
    -0.36
    ffilm
    -0.35
    }();
    -0.34
     Normdatei
    -0.33
     rodilla
    -0.33
     considérons
    -0.31
    POSITIVE LOGITS
    tableFuture
    0.54
    GEBURTSDATUM
    0.51
    tiful
    0.50
    uset
    0.47
    Према
    0.46
    nages
    0.45
     transférez
    0.44
    VIAF
    0.44
    engu
    0.44
    eref
    0.43
    Activations Density 0.061%

    No Known Activations