© 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. 63499
    Prev
    Next
    INDEX
    Explanations

    terms related to hierarchy and ranking in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SaveChanges
    -0.52
     idéia
    -0.48
     caneta
    -0.46
    símbolo
    -0.46
     Tabelle
    -0.46
    cheinend
    -0.46
     poupée
    -0.45
     programação
    -0.45
     pizarra
    -0.45
     venganza
    -0.44
    POSITIVE LOGITS
    First
    0.79
    first
    0.71
     First
    0.70
    FIRST
    0.64
     first
    0.64
     facie
    0.61
     FIRST
    0.60
    ########.
    0.59
     getFirst
    0.59
    posedge
    0.58
    Activations Density 0.015%

    No Known Activations