© 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. 24-GEMMASCOPE-RES-16K
    11. 5369
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to data parameters in a structured format

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

    Tokens after "1" followed by a non-alphanumeric character

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and identifiers

    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
    CloseOperation
    -0.70
     صوتيه
    -0.70
     snippetHide
    -0.70
     beginnetje
    -0.68
     Administrativna
    -0.67
    最快更新
    -0.65
     تضيفلها
    -0.62
    angelog
    -0.61
     թվական
    -0.60
    StructEnd
    -0.60
    POSITIVE LOGITS
    Carrière
    0.40
    fromnode
    0.34
    s
    0.33
    QMetaType
    0.32
     Macro
    0.31
     Himo
    0.31
     Tad
    0.30
    Macro
    0.29
    zzleHttp
    0.29
    i
    0.29
    Activations Density 1.182%

    No Known Activations