© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    phrases that express awareness or acknowledgment of facts or beliefs

    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
     unknownFields
    -0.76
    Personensuche
    -0.76
     disambiguazione
    -0.70
     initState
    -0.67
    ValueStyle
    -0.65
     SEDS
    -0.64
    ()?;
    -0.63
     ujednoznacz
    -0.62
    aarrggbb
    -0.61
    ArrowToggle
    -0.60
    POSITIVE LOGITS
     tonight
    0.61
     الرخصة
    0.61
    umumkan
    0.57
     contemporaine
    0.53
     this
    0.52
    __':
    0.52
     Tonight
    0.52
     Supernatural
    0.51
    enumi
    0.51
     charité
    0.51
    Activations Density 0.335%

    No Known Activations