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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 64644
    Prev
    Next
    INDEX
    Explanations

    complex and abstract ideas that are difficult to articulate

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

    words that are hard to explain

    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
     Roskov
    -0.49
     Solon
    -0.49
    ⓘ
    -0.45
     Obrador
    -0.45
    cipar
    -0.43
    Fiscal
    -0.42
    UnusedPrivate
    -0.42
    apunov
    -0.42
     Avid
    -0.42
     Fiscal
    -0.41
    POSITIVE LOGITS
     sentía
    0.51
     indefin
    0.43
     siente
    0.43
     gustaba
    0.42
     sentirse
    0.42
     sensación
    0.41
     <=",
    0.41
     vaguely
    0.41
     feels
    0.40
     sensação
    0.40
    Activations Density 0.045%

    No Known Activations