© 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. 38754
    Prev
    Next
    INDEX
    Explanations

    references to zeros, zeroes, or empty structures

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

    zeros and absence

    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
     might
    -0.49
    Supplied
    -0.43
     radi
    -0.42
    instancetype
    -0.41
    Radi
    -0.41
     supplied
    -0.40
    autorest
    -0.40
     pié
    -0.39
     lieber
    -0.38
    IActionResult
    -0.38
    POSITIVE LOGITS
    zeros
    3.19
     zeros
    2.02
    Zeros
    1.50
     zeroes
    1.38
    zero
    1.03
     Zero
    1.03
     ZERO
    1.01
    Zero
    1.00
     zero
    1.00
    ZERO
    0.93
    Activations Density 0.001%

    No Known Activations