© 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. 73726
    Prev
    Next
    INDEX
    Explanations

    scientific terms and numerical data related to measurements and analyses

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

    analysis software, delivery, or stain

    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
    Hozzáférés
    -0.40
    HasForeignKey
    -0.34
    AddHtmlAttribute
    -0.33
     destrucción
    -0.32
     rozwią
    -0.32
    )))),
    -0.32
    )))));
    -0.32
     dinosaurio
    -0.31
    })),
    -0.31
     žele
    -0.31
    POSITIVE LOGITS
    Personendaten
    1.00
    verwijspagina
    0.91
    LookAnd
    0.81
    ?),
    0.75
    ?)
    0.73
     ?)
    0.73
    ſelf
    0.72
    !)
    0.71
    !!)
    0.70
    °)
    0.69
    Activations Density 3.575%

    No Known Activations