© 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. 35-GEMMASCOPE-RES-16K
    11. 14538
    Prev
    Next
    INDEX
    Explanations

    phrases that begin with "According to" followed by various sources or testimony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.60
     <=",
    -0.44
     doubted
    -0.44
     AppCompatTheme
    -0.44
    addContainerGap
    -0.44
     SwitchCompat
    -0.43
     nakalista
    -0.42
    RTSC
    -0.41
    oredCriteria
    -0.40
    MigrationBuilder
    -0.40
    POSITIVE LOGITS
     reports
    0.77
     estimates
    0.69
     calculations
    0.67
     recent
    0.62
     uppgifter
    0.60
     Angaben
    0.60
     instructions
    0.59
     testimony
    0.59
     preliminary
    0.57
     estimations
    0.57
    Activations Density 0.257%

    No Known Activations