© 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. 9-GEMMASCOPE-RES-16K
    6. 10902
    Prev
    Next
    INDEX
    Explanations

    HTML and structural elements commonly used in web development and programming documentation

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

    HTML and LaTeX size tags

    np_acts-logits-general · gemini-2.0-flash

    small font formatting markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.80
    httphttps
    -0.76
    styleType
    -0.75
     propOrder
    -0.73
     صوتيه
    -0.71
    uxxxx
    -0.71
    rungsseite
    -0.69
    SourceChecksum
    -0.65
     disambiguazione
    -0.65
    RenderAtEndOf
    -0.65
    POSITIVE LOGITS
    scriptsize
    0.45
    footnotesize
    0.44
    <h6>
    0.36
    small
    0.32
     싶
    0.31
     juntas
    0.31
     mesto
    0.31
     watermark
    0.31
    note
    0.30
    ToDecimal
    0.30
    Activations Density 0.979%

    No Known Activations