© 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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5117
    Prev
    Next
    INDEX
    Explanations

    structured data or numerical information typically found in reports or protocols

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

    Abbreviations followed by definitions

    np_acts-logits-general · gemini-2.0-flash

    technical and foreign words

    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
     orina
    -0.32
     antemano
    -0.32
     plazos
    -0.31
     acá
    -0.30
     afecto
    -0.30
     libremente
    -0.30
     cooperación
    -0.28
     funcionarios
    -0.28
    ándolos
    -0.28
     puentes
    -0.28
    POSITIVE LOGITS
     $_(
    0.90
     autorytatywna
    0.88
     الاطلاع
    0.83
     queſta
    0.81
     Administrativna
    0.78
    extAlignment
    0.76
     ―――――
    0.76
    𖡻
    0.75
    ValueStyle
    0.73
    <unused3>
    0.73
    Activations Density 0.502%

    No Known Activations