© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1397
    Prev
    Next
    INDEX
    Explanations

    technical details related to cooking appliances and methods

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

    Actions performed on samples or mixtures

    np_acts-logits-general · gemini-2.0-flash

    shaking, mixing, or heating in chambers

    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
    NamedQueries
    -0.46
    quisite
    -0.44
     '\\;'
    -0.43
    afterEach
    -0.42
    OPHY
    -0.42
    Vanjske
    -0.42
    reordered
    -0.42
    цезда
    -0.41
     فريبيس
    -0.41
    pius
    -0.40
    POSITIVE LOGITS
    InteropServices
    0.52
    RegistryLite
    0.48
    oa̍t
    0.40
    条件
    0.39
    LayoutPanel
    0.38
    XmlRootElement
    0.38
    IsMutable
    0.36
     Oxygen
    0.36
     Lucerne
    0.35
    preven
    0.35
    Activations Density 0.380%

    No Known Activations