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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 10305
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts

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

    "temporary" files or states

    np_acts-logits-general · gemini-2.0-flash

    temporary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.66
     kasarigan
    -0.50
    CppCodeGen
    -0.48
    ExtendWith
    -0.45
    NavigationView
    -0.40
    :✨
    -0.38
    hyrchwyd
    -0.37
    يميديا
    -0.37
     ſou
    -0.36
    oa̍t
    -0.36
    POSITIVE LOGITS
     temporary
    3.23
     Temporary
    2.81
     temporarily
    2.75
    temporary
    2.69
    Temporary
    2.61
     tijde
    2.33
     temporaire
    2.30
     Tempor
    2.23
    tempor
    2.22
    临时
    2.20
    Activations Density 0.880%

    No Known Activations