© 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. 17-GEMMASCOPE-RES-16K
    11. 13006
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "de" in various contexts, indicating a focus on possessive or descriptive relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -1.04
     Efq
    -1.02
     himſelf
    -1.02
     Anſ
    -1.01
     itſelf
    -0.97
     Chriftian
    -0.93
     Hift
    -0.92
     myſelf
    -0.92
     becauſe
    -0.91
     uſed
    -0.87
    POSITIVE LOGITS
     the
    0.76
    Σε
    0.74
     course
    0.70
     a
    0.68
    '){
    0.67
    '>
    0.67
    course
    0.66
     de
    0.66
     De
    0.65
    )':
    0.64
    Activations Density 0.018%

    No Known Activations