© 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. 3-GEMMASCOPE-RES-16K
    11. 5876
    Prev
    Next
    INDEX
    Explanations

    statements regarding the condition and status of subjects 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distal
    -0.45
     Hanks
    -0.45
    Symfony
    -0.44
    azia
    -0.43
    icii
    -0.43
     olan
    -0.42
    Superclass
    -0.42
    ніципалі
    -0.42
     Heine
    -0.41
     Rig
    -0.41
    POSITIVE LOGITS
     مشين
    0.78
     Wikimedijinoj
    0.76
    =$?
    0.72
    tagHelperRunner
    0.69
    MethodManager
    0.68
     referenties
    0.67
    AnchorStyles
    0.66
     -*-
    0.66
    Còn
    0.65
     Вікі
    0.63
    Activations Density 0.758%

    No Known Activations