Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 108647
    Prev
    Next
    INDEX
    Explanations

    terms related to leashes and dog training equipment

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

    legal, technical, and medical abbreviations

    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
    Parcelize
    -0.66
     كومونز
    -0.51
     corris
    -0.48
     underlies
    -0.47
     Grüsse
    -0.47
     underlie
    -0.46
     ingest
    -0.46
     oreja
    -0.45
     reproduce
    -0.44
     CURLOPT
    -0.43
    POSITIVE LOGITS
     Nikki
    0.79
    Nikki
    0.69
     numOf
    0.68
    numOf
    0.67
    mensaje
    0.63
    LError
    0.60
     leash
    0.59
     flashlight
    0.54
     mensaje
    0.51
    jshint
    0.51
    Activations Density 0.004%

    No Known Activations