© 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. 25-GEMMASCOPE-RES-16K
    11. 1466
    Prev
    Next
    INDEX
    Explanations

    references to films and their associated elements, such as details about their inspiration and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.53
    Autoritní
    -0.53
    ętr
    -0.49
     vœux
    -0.49
    ScopeManager
    -0.48
    abetta
    -0.47
    archiviato
    -0.46
    uxxxx
    -0.46
    RequestParam
    -0.46
    igshid
    -0.46
    POSITIVE LOGITS
     copied
    1.77
     imitation
    1.73
     copying
    1.71
     imitate
    1.70
     imit
    1.68
     imitating
    1.68
     mimic
    1.67
     imitated
    1.65
     emulate
    1.60
     copy
    1.60
    Activations Density 0.823%

    No Known Activations