© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4164
    Prev
    Next
    INDEX
    Explanations

    specific types of medical terminologies related to cancer and anatomical structures

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

    Preceding certain articles or determiners

    np_acts-logits-general · gemini-2.0-flash

    non-grammatical determiners and articles

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    XtraReports
    -0.44
     clín
    -0.43
    ByVersion
    -0.42
     fotográfico
    -0.41
    ądze
    -0.40
     entregado
    -0.40
     cubierto
    -0.38
     yür
    -0.38
     toalha
    -0.37
     morango
    -0.36
    POSITIVE LOGITS
     Италијани
    0.46
    ViewImports
    0.46
     PNP
    0.44
     PDA
    0.44
     stripper
    0.44
    ктан
    0.44
     resourceCulture
    0.43
    LookAnd
    0.43
    MockMvc
    0.40
     Taliban
    0.40
    Activations Density 0.720%

    No Known Activations