© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6977
    Prev
    Next
    INDEX
    Explanations

    a high concentration of periods indicating sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.00
    ↵
    -0.74
    ↵↵↵
    -0.73
    <eos>
    -0.62
    ↵↵↵↵↵↵↵
    -0.58
    ↵↵↵↵
    -0.58
    ↵↵↵↵↵
    -0.57
    </h3>
    -0.54
    ."
    -0.53
    ↵↵↵↵↵↵
    -0.52
    POSITIVE LOGITS
    parsedMessage
    0.71
     كومونز
    0.71
    Datuak
    0.66
    verwijspagina
    0.65
    脚注の使い方
    0.64
    LookAnd
    0.63
     صوتيه
    0.63
    DebuggerNonUser
    0.63
    󠁮
    0.63
     تضيفلها
    0.63
    Activations Density 0.482%

    No Known Activations