© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14698
    Prev
    Next
    INDEX
    Explanations

    specific medical or automotive recall scenarios

    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
     AssemblyTitle
    -0.65
     Olom
    -0.54
    realme
    -0.52
     menino
    -0.52
    ียม
    -0.51
    providedIn
    -0.51
    jetty
    -0.51
     organizada
    -0.50
     Muc
    -0.49
     promises
    -0.48
    POSITIVE LOGITS
     model
    1.77
     models
    1.68
     Model
    1.50
     Models
    1.49
    model
    1.49
     modelo
    1.43
    Model
    1.40
     MODEL
    1.38
     modèle
    1.37
     modelos
    1.36
    Activations Density 0.308%

    No Known Activations