© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8189
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical or alphanumeric sequences indicating data IDs or codes

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

    Characters after hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal characters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.94
    WebVitals
    -0.87
    #+#
    -0.81
    MigrationBuilder
    -0.79
     дописавши
    -0.78
     BoxDecoration
    -0.75
    İstinadlar
    -0.74
    MemoryWarning
    -0.74
    NameInMap
    -0.73
    UIControlState
    -0.72
    POSITIVE LOGITS
     énergé
    0.44
     sélectionnés
    0.42
    ेशा
    0.41
     apó
    0.41
     alone
    0.37
     fermés
    0.37
     ED
    0.36
     ketiga
    0.36
    žad
    0.36
    /</
    0.35
    Activations Density 0.301%

    No Known Activations