© 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. 416
    Prev
    Next
    INDEX
    Explanations

    PHP variables and arrays related to form handling

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

    Code-related terms and system variables

    np_acts-logits-general · gemini-2.0-flash

    programming code and requests

    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
    toBeTruthy
    -0.39
     fine
    -0.37
     Pear
    -0.35
     clubs
    -0.35
     FINE
    -0.33
     can
    -0.33
    ,=
    -0.32
    <bos>
    -0.32
    slidesPer
    -0.32
     in
    -0.31
    POSITIVE LOGITS
    AccessorTable
    0.81
    MessageTagHelper
    0.80
     AssemblyTitle
    0.76
    IntoConstraints
    0.71
    StoryboardSegue
    0.65
     تانيه
    0.65
    ValueStyle
    0.64
    GEBURTSDATUM
    0.64
     للمعارف
    0.63
    errHandler
    0.63
    Activations Density 0.074%

    No Known Activations