© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3871
    Prev
    Next
    INDEX
    Explanations

    elements related to data analytics and computer science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.92
     Roskov
    -0.87
    Vidite
    -0.84
    WebVitals
    -0.84
     AssemblyCulture
    -0.83
    InjectAttribute
    -0.79
    oredCriteria
    -0.79
     kasarigan
    -0.75
    webElementXpaths
    -0.75
    bootstrapcdn
    -0.75
    POSITIVE LOGITS
     respondeu
    0.44
     deveria
    0.43
     ότι
    0.40
     communis
    0.39
    kosh
    0.39
    cence
    0.38
     mittleren
    0.37
     explicou
    0.37
     viagens
    0.36
    «
    0.35
    Activations Density 0.789%

    No Known Activations