© 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. 8-GEMMASCOPE-RES-16K
    11. 4967
    Prev
    Next
    INDEX
    Explanations

    instances of movement or actions related to exploration and navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harapan
    -0.47
     siihen
    -0.45
    unger
    -0.42
    طلب
    -0.42
     opener
    -0.41
     liitty
    -0.40
    erek
    -0.40
    [
    -0.40
     esfuerzo
    -0.39
     flamme
    -0.39
    POSITIVE LOGITS
     дописавши
    1.04
    NameInMap
    1.00
     roaming
    0.98
    tagHelperRunner
    0.93
    hyrchwyd
    0.89
    CppMethod
    0.87
     roam
    0.86
     المعيارى
    0.86
    __":
    0.85
     wandering
    0.84
    Activations Density 0.377%

    No Known Activations