© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5367
    Prev
    Next
    INDEX
    Explanations

    expressions related to filling or completing spaces or items

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

    "fill" or "filling"

    np_acts-logits-general · gemini-2.0-flash

    filling gaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -1.00
     GenerationType
    -0.87
     AssemblyProduct
    -0.86
    Personendaten
    -0.70
    AndEndTag
    -0.64
    OrNil
    -0.61
     ModelExpression
    -0.61
    ValueStyle
    -0.61
    SourceChecksum
    -0.60
    enderror
    -0.58
    POSITIVE LOGITS
     gaps
    1.13
     Gaps
    0.96
     gap
    0.94
    gaps
    0.93
     voids
    0.87
    gap
    0.83
     coffers
    0.80
     void
    0.78
    Gap
    0.78
     holes
    0.76
    Activations Density 0.108%

    No Known Activations