© 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. 30-GEMMASCOPE-RES-16K
    11. 12648
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming concepts related to input/output operations

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

    Code-related text

    np_acts-logits-general · gemini-2.0-flash

    job application interviews

    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
     MainAxisSize
    -0.46
    ContentLoaded
    -0.37
    Hochspringen
    -0.36
    ongiorno
    -0.31
    ➟
    -0.30
    hbs
    -0.29
    婪
    -0.29
    Clik
    -0.29
     kesan
    -0.29
    objet
    -0.28
    POSITIVE LOGITS
     submission
    0.76
     submissions
    0.76
     Submissions
    0.71
     Submission
    0.71
     SUBMIT
    0.68
     contestants
    0.65
     Contest
    0.65
    submission
    0.64
    Submissions
    0.63
     submitting
    0.62
    Activations Density 0.694%

    No Known Activations