© 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. 15-GEMMASCOPE-RES-16K
    11. 1419
    Prev
    Next
    INDEX
    Explanations

    sentences expressing difficulty, struggle, or emotional conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.74
    Hauptartikel
    -0.70
    出版年
    -0.69
    fromnode
    -0.68
    ]")]
    -0.67
    migrationBuilder
    -0.67
    oredCriteria
    -0.67
     GenerationType
    -0.66
     <<<<<<<<<<<<<<
    -0.62
    DockStyle
    -0.62
    POSITIVE LOGITS
     muster
    0.67
     convincing
    0.66
     adequately
    0.64
     convince
    0.61
     adequate
    0.57
     sufficient
    0.57
     sufficiently
    0.55
     accurately
    0.51
     Adequate
    0.50
     persuading
    0.49
    Activations Density 0.359%

    No Known Activations