© 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. 152
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-like structures relevant to programming

    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
     vermelhas
    -0.47
     dieux
    -0.47
     journaux
    -0.47
     engraçadas
    -0.43
     florales
    -0.42
     femininas
    -0.41
     vérit
    -0.40
     nuages
    -0.40
     artificiales
    -0.39
     desmotivaciones
    -0.38
    POSITIVE LOGITS
    Datuak
    0.76
    GEBURTSDATUM
    0.71
    verwijspagina
    0.69
     TAMBÉM
    0.66
    Geplaatst
    0.66
     Meksiku
    0.66
     DELLE
    0.64
    İY
    0.63
    oredCriteria
    0.63
     TÉCNICA
    0.63
    Activations Density 0.103%

    No Known Activations