© 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. 31-GEMMASCOPE-RES-131K
    11. 37849
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pass" and its variations, indicating a focus on actions related to transferring or conveying something

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

    pass on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.41
    OGND
    -0.40
    فایل‌لار
    -0.37
    newswire
    -0.36
    BeginInit
    -0.36
     fonte
    -0.36
    JvmStatic
    -0.36
      (
    -0.36
    SOUNDBITE
    -0.35
    脚注の使い方
    -0.35
    POSITIVE LOGITS
     passing
    1.02
    Passing
    1.01
     passed
    1.00
    Pass
    0.98
     passes
    0.97
     pass
    0.97
    passing
    0.97
     Passed
    0.96
     Pass
    0.95
    pass
    0.92
    Activations Density 0.013%

    No Known Activations