© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 106720
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ranger" and its variations, indicating a focus on park or outdoor rangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Ranger boats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freitas
    -0.38
    切
    -0.38
     Carvalho
    -0.33
    AxisAlignment
    -0.32
     Guimarães
    -0.32
    衷
    -0.32
     Koll
    -0.30
     Bö
    -0.30
    FILL
    -0.30
     opulent
    -0.30
    POSITIVE LOGITS
     Ranger
    2.47
    Ranger
    2.28
     ranger
    2.20
    ranger
    1.88
     rangers
    1.87
     Rangers
    1.70
    Rangers
    1.56
    ANGER
    0.96
     forester
    0.89
    raptor
    0.83
    Activations Density 0.007%

    No Known Activations