© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 23723
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Collins."

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

    Collins

    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
    RegressionTest
    -0.64
     pleaſure
    -0.62
     greateſt
    -0.52
    pakah
    -0.52
     ſtate
    -0.51
     purpoſe
    -0.48
     ſte
    -0.48
    GraphicsUnit
    -0.48
     byteArray
    -0.48
     ***!
    -0.47
    POSITIVE LOGITS
     Collins
    2.53
    Collins
    2.38
     COLLINS
    2.22
     Collin
    1.23
    coll
    1.09
     coll
    1.06
     Coll
    0.90
    Coll
    0.89
    COLL
    0.88
     colline
    0.75
    Activations Density 0.003%

    No Known Activations