© 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. 23-GEMMASCOPE-RES-16K
    11. 11080
    Prev
    Next
    INDEX
    Explanations

    phrases or terms associated with specific physical sensations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.91
     Theſe
    -0.85
     Reſ
    -0.85
    úsqueda
    -0.83
     myſelf
    -0.79
     Houſe
    -0.78
     Diſ
    -0.77
     pleaſure
    -0.75
     Eſ
    -0.75
     Efq
    -0.74
    POSITIVE LOGITS
     la
    0.70
     si
    0.64
     pe
    0.63
     care
    0.61
     de
    0.61
     sa
    0.56
     une
    0.50
     sau
    0.50
     mas
    0.49
     co
    0.49
    Activations Density 0.029%

    No Known Activations