© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    references to digital object identifiers (DOIs) or links for academic articles and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs and formatting related to digital object identifiers (DOIs) and citations

    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
     فريبيس
    -0.65
    RenderAtEndOf
    -0.57
    جغرافيا
    -0.57
     ExecuteAsync
    -0.57
    anskje
    -0.53
    HostException
    -0.52
     angesch
    -0.52
     cober
    -0.51
    }");
    -0.51
    exitRule
    -0.49
    POSITIVE LOGITS
    Doi
    0.80
    doi
    0.78
     doi
    0.72
     DOI
    0.72
    DOI
    0.69
     Doi
    0.69
    Geplaatst
    0.66
     referenties
    0.63
     kasarigan
    0.62
     nakalista
    0.57
    Activations Density 0.399%

    No Known Activations