© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appearance" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     fer
    -0.48
     fra
    -0.47
     fier
    -0.47
     Nord
    -0.46
     voli
    -0.45
     bul
    -0.45
    aler
    -0.44
    ular
    -0.44
     Tiger
    -0.44
     Ranger
    -0.44
    POSITIVE LOGITS
     Appearances
    0.88
     appearances
    0.85
    appearance
    0.67
     appearance
    0.67
    \{\\
    0.67
     Appearance
    0.66
     apparaissent
    0.65
     EconPapers
    0.65
    Appearances
    0.62
    verifyException
    0.62
    Activations Density 0.332%

    No Known Activations