© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5124
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure indicators often found in scientific research documents

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

    physics publications

    np_acts-logits-general · gemini-2.0-flash

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     الحره
    -0.58
    liceerd
    -0.52
     autorytatywna
    -0.47
    httphttps
    -0.45
    Personendaten
    -0.45
     indisponible
    -0.44
     تكبرها
    -0.43
    GTCX
    -0.43
    الإنجليزية
    -0.42
    "])
    -0.42
    POSITIVE LOGITS
    SpringBootTest
    0.44
    MigrationBuilder
    0.42
    ViewFeatures
    0.40
    Viited
    0.36
    assets
    0.36
    Value
    0.35
    woche
    0.35
    Labor
    0.33
     Bank
    0.33
    wochen
    0.33
    Activations Density 0.278%

    No Known Activations