© 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. 23-GEMMASCOPE-RES-16K
    11. 14826
    Prev
    Next
    INDEX
    Explanations

    numeric data, particularly formatted numbers and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.68
     SIX
    -0.67
    interopRequire
    -0.65
     sixth
    -0.61
     fifth
    -0.60
     six
    -0.59
     nahilalakip
    -0.59
    DockStyle
    -0.59
    SIX
    -0.58
     chi̍t
    -0.57
    POSITIVE LOGITS
     Tenth
    0.65
    9
    0.60
     Ninth
    0.56
     Ninety
    0.55
    UnusedPrivate
    0.54
     Nine
    0.54
     Capricorn
    0.50
     centenary
    0.50
     समीक्षक
    0.50
    cluso
    0.48
    Activations Density 0.414%

    No Known Activations