© 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. 11631
    Prev
    Next
    INDEX
    Explanations

    phrases related to going out or engaging in activities

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

    "Out" or related terms

    np_acts-logits-general · gemini-2.0-flash

    going out

    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
    Архівовано
    -0.50
    ReusableCell
    -0.48
    ArgsConstructor
    -0.47
    sizeCache
    -0.46
    KommentareTeilen
    -0.41
    دانشنامهٔ
    -0.40
    原始内容存档于
    -0.40
    AndEndTag
    -0.39
    aarrggbb
    -0.37
    ipelago
    -0.35
    POSITIVE LOGITS
     outings
    1.06
     public
    1.05
    外出
    0.96
    出門
    0.93
    出门
    0.91
     outing
    0.90
     outdoors
    0.84
     everywhere
    0.84
     shopping
    0.83
     places
    0.76
    Activations Density 0.310%

    No Known Activations