© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5526
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate evidence or proof in discussions

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

    "as is" or "as evidenced by"

    np_acts-logits-general · gemini-2.0-flash

    evidenced by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.49
    ſelves
    -0.48
    tagHelperRunner
    -0.44
    addGap
    -0.44
    StructEnd
    -0.42
    Життєпис
    -0.42
     Sicilian
    -0.41
    setCellStyle
    -0.40
     oprot
    -0.40
    principalColumn
    -0.40
    POSITIVE LOGITS
     evidenced
    0.52
    observable
    0.48
    IBOutlet
    0.47
     evident
    0.47
     nahilalakip
    0.45
     indik
    0.43
     manifested
    0.43
     Indication
    0.43
     indication
    0.42
    testens
    0.41
    Activations Density 0.882%

    No Known Activations