© 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. 10219
    Prev
    Next
    INDEX
    Explanations

    cautions and warnings related to careful decision-making in various contexts

    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
     незавершена
    -0.69
    LookAnd
    -0.58
    AddTagHelper
    -0.55
    ResponseWriter
    -0.53
    Initializable
    -0.53
    Externé
    -0.52
    writeField
    -0.51
    panou
    -0.49
     basta
    -0.49
    odils
    -0.48
    POSITIVE LOGITS
     careful
    2.00
     care
    1.78
     Careful
    1.75
    Careful
    1.73
     caution
    1.69
     carefully
    1.67
    care
    1.65
     cautious
    1.52
    Care
    1.48
     Carefully
    1.42
    Activations Density 0.359%

    No Known Activations