© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7577
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in the text

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

    Text within square brackets

    np_acts-logits-general · gemini-2.0-flash

    Rajki Rajaram

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.81
    хьтан
    -0.70
    tagHelperRunner
    -0.68
     wikipagina
    -0.67
    SequentialGroup
    -0.67
     يتيمه
    -0.65
    MigrationBuilder
    -0.65
     '\\;'
    -0.65
    parsedMessage
    -0.64
    الحياه
    -0.63
    POSITIVE LOGITS
    eseorang
    0.38
    ↵↵
    0.37
    tegra
    0.34
    )
    0.33
     Out
    0.32
     eg
    0.32
    ご了承ください
    0.30
     Live
    0.29
     elegan
    0.29
    Out
    0.29
    Activations Density 0.383%

    No Known Activations