© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 52113
    Prev
    Next
    INDEX
    Explanations

    connections and possibilities within given contexts or situations

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

    verbs describing actions or findings

    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
    In
    -0.28
     собой
    -0.25
    James
    -0.24
    BE
    -0.23
    in
    -0.23
    Post
    -0.23
    A
    -0.22
     Sommer
    -0.22
    NSArray
    -0.22
    くい
    -0.22
    POSITIVE LOGITS
     صوتيه
    1.02
     Infórmanos
    0.94
    MigrationBuilder
    0.93
    ########.
    0.93
    ConstraintMaker
    0.90
     Normdatei
    0.90
    ]")]
    0.89
    exitRule
    0.89
     الحره
    0.88
    <unused79>
    0.87
    Activations Density 0.271%

    No Known Activations