© 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. 9-GEMMASCOPE-RES-16K
    11. 8186
    Prev
    Next
    INDEX
    Explanations

    pronouns and forms of the verb "to be" to express personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ijão
    -0.60
     parah
    -0.57
    dymyr
    -0.54
     zog
    -0.52
    mo
    -0.52
    Bes
    -0.52
    зика
    -0.51
     vaik
    -0.51
    lenz
    -0.51
     samoz
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    1.04
    Datuak
    1.02
    expandindo
    0.92
     صوتيه
    0.81
    .*")]
    0.79
    HasAnnotation
    0.75
     متعلقه
    0.75
     تانيه
    0.73
    pushFollow
    0.72
     للمعارف
    0.72
    Activations Density 0.211%

    No Known Activations