© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3263
    Prev
    Next
    INDEX
    Explanations

    references to word puzzles, particularly crossword or acrostic formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disposição
    -0.37
     rainha
    -0.36
     '))
    -0.33
     extérieur
    -0.33
    ')))
    -0.31
    rungsseite
    -0.31
     engran
    -0.31
     vše
    -0.30
     criatura
    -0.30
     protectora
    -0.29
    POSITIVE LOGITS
    Personendaten
    1.30
    verwijspagina
    1.05
    LookAnd
    0.74
     kasarigan
    0.69
    )."
    0.69
    !!)
    0.69
    ?).
    0.69
    ?),
    0.68
    !!!)
    0.68
    ??)
    0.67
    Activations Density 5.916%

    No Known Activations