© 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. 4-GEMMASCOPE-RES-16K
    11. 2876
    Prev
    Next
    INDEX
    Explanations

    words related to intensity, effectiveness, and characteristic qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.72
    mtable
    -0.54
     IndexPath
    -0.52
    Gambas
    -0.52
     BorderSide
    -0.51
     Yn
    -0.50
     Halley
    -0.50
     /\.
    -0.49
    /**
    -0.49
    يميديا
    -0.49
    POSITIVE LOGITS
     grace
    0.71
     momentum
    0.71
     CreateTagHelper
    0.69
     vigor
    0.68
     credibility
    0.67
     للاسماء
    0.66
     flexibility
    0.66
     courage
    0.65
     potency
    0.64
     finesse
    0.64
    Activations Density 0.758%

    No Known Activations