© 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. 24-GEMMASCOPE-RES-16K
    6. 12085
    Prev
    Next
    INDEX
    Explanations

    words related to legal status and identity rights, particularly in regard to marriage equality

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

    Tokens preceding specific words: same, stand, zero, break, random, life, field, single

    np_acts-logits-general · gemini-2.0-flash

    compound words and hyphenated phrases

    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
    tvguidetime
    -1.18
     مشين
    -1.15
    LookAnd
    -1.13
     ExecuteAsync
    -1.09
     Италијани
    -1.06
    OGND
    -1.05
    ConstraintMaker
    -1.02
    \{\\
    -1.02
    parsedMessage
    -1.01
    İstinadlar
    -0.98
    POSITIVE LOGITS
    -
    1.30
    –
    0.91
     -
    0.88
     –
    0.78
    =
    0.77
    --
    0.74
    −
    0.63
    -
    0.60
    —
    0.59
    ~
    0.57
    Activations Density 0.740%

    No Known Activations