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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9335
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols, indicating emphasis or structure in the text

    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
    nourriture
    -0.56
    baarheid
    -0.55
    boneca
    -0.55
    télé
    -0.53
    brinco
    -0.50
    guiente
    -0.49
    arbitrary
    -0.48
    gården
    -0.48
    eſ
    -0.48
    caneca
    -0.46
    POSITIVE LOGITS
     Shakspeare
    1.03
     Cæsar
    0.86
     Monfieur
    0.86
     pleaſure
    0.84
     canst
    0.83
     Majefty
    0.82
     Shaksp
    0.81
     Mahomet
    0.77
     Diſ
    0.75
     Spinoza
    0.74
    Activations Density 0.175%

    No Known Activations