© 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. 24-GEMMASCOPE-RES-16K
    11. 6672
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experience and subjective assessments

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

    Follows commas, especially at the start of clauses

    np_acts-logits-general · gemini-2.0-flash

    clause boundary followed by conjunction

    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
     ujednoznacz
    -0.45
    migrationBuilder
    -0.45
    verwijspagina
    -0.44
    djangoproject
    -0.42
    chenkt
    -0.42
     AssemblyVersion
    -0.41
    wapV
    -0.40
     Taktlose
    -0.40
    Демографія
    -0.39
    .*")]
    -0.39
    POSITIVE LOGITS
     that
    0.59
     bahwa
    0.49
     HasFactory
    0.48
    medriver
    0.47
     rằng
    0.45
     ότι
    0.40
     kwamba
    0.40
    CompleteListener
    0.40
    ว่า
    0.39
    pośred
    0.38
    Activations Density 0.641%

    No Known Activations