© 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. 859
    Prev
    Next
    INDEX
    Explanations

    intensifiers that emphasize quality or status

    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
     absc
    -0.69
     brû
    -0.62
     Engel
    -0.61
     scrubs
    -0.60
     Clau
    -0.59
    ="@+
    -0.58
     térmica
    -0.58
     Pence
    -0.57
    кор
    -0.57
     Xbox
    -0.57
    POSITIVE LOGITS
    highly
    2.12
     highly
    2.10
     Highly
    2.02
    Highly
    2.01
     altamente
    1.58
     hugely
    1.11
     strongly
    1.09
     heavily
    1.07
     fortement
    1.05
     greatly
    1.01
    Activations Density 0.117%

    No Known Activations