Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 16332
    Prev
    Next
    INDEX
    Explanations

    phrases related to alerts and warnings regarding potential dangers or hazards

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

    alerts or caution

    np_acts-logits-general · gemini-2.0-flash

    warning and alert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     OFDb
    -0.64
    FormTagHelper
    -0.53
    زینه
    -0.53
    WireFormatLite
    -0.53
    ソッド
    -0.52
     Censo
    -0.52
     nahilalakip
    -0.52
    MigrationBuilder
    -0.52
     Familienname
    -0.52
    TestRunner
    -0.51
    POSITIVE LOGITS
     warning
    2.58
     warnings
    2.34
     Warning
    2.17
     warn
    2.09
    warning
    2.02
     warned
    1.98
     warns
    1.96
    Warning
    1.95
     Warnings
    1.92
     WARNING
    1.92
    Activations Density 0.259%

    No Known Activations