© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to image processing and resizing

    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
    AndEndTag
    -0.86
    Personensuche
    -0.59
     nakalista
    -0.58
    :✨
    -0.57
     avanti
    -0.54
    </thead>
    -0.52
    yuki
    -0.51
    GeneratedCode
    -0.50
     Nye
    -0.48
    ########.
    -0.47
    POSITIVE LOGITS
     width
    1.18
     Width
    1.10
    width
    1.02
    Width
    1.01
     dimensions
    0.99
     widths
    0.94
     height
    0.89
     WIDTH
    0.87
     proportions
    0.86
     Dimensions
    0.85
    Activations Density 0.462%

    No Known Activations