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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12946
    Prev
    Next
    INDEX
    Explanations

    words that indicate possession, maintaining attention, and referencing standards or limitations

    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
    хьтан
    -0.62
    bootstrapcdn
    -0.53
    annica
    -0.48
    TestingModule
    -0.48
    tslib
    -0.47
    gridx
    -0.47
     متعلقه
    -0.45
    λιά
    -0.45
    ArgsConstructor
    -0.44
    iestety
    -0.44
    POSITIVE LOGITS
     mind
    3.43
    mind
    2.66
     Mind
    2.46
    Mind
    2.39
     MIND
    2.38
     minds
    2.29
    MIND
    1.96
     mente
    1.86
    minds
    1.68
     Minds
    1.57
    Activations Density 0.191%

    No Known Activations