© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10171
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize self-reference or the concept of "itself."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JADX
    -0.72
     Samaria
    -0.70
    SBATCH
    -0.68
     optique
    -0.66
     expériment
    -0.65
    UnusedPrivate
    -0.64
     unknownFields
    -0.64
    اعمال
    -0.64
    providedIn
    -0.63
     électriques
    -0.63
    POSITIVE LOGITS
     itself
    1.36
     its
    1.23
    itself
    1.10
    它
    0.99
    its
    0.96
    Its
    0.96
    它的
    0.95
     Its
    0.94
     它
    0.85
     ITS
    0.84
    Activations Density 0.048%

    No Known Activations