© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1842
    Prev
    Next
    INDEX
    Explanations

    sections related to notable events or milestones

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    beginnings of sentences or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -1.08
    ſcher
    -1.05
     AssemblyCulture
    -1.05
    <pad>
    -1.05
    <unused41>
    -1.05
    <unused23>
    -1.04
    <unused28>
    -1.04
    <unused17>
    -1.04
    [@BOS@]
    -1.04
    <unused14>
    -1.04
    POSITIVE LOGITS
    ↵↵
    0.82
    The
    0.73
    <blockquote>
    0.72
    I
    0.70
    As
    0.66
    A
    0.65
    1
    0.62
    In
    0.62
    We
    0.61
    For
    0.59
    Activations Density 0.925%

    No Known Activations