© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 78008
    Prev
    Next
    INDEX
    Explanations

    spaces or pauses in the text

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

    conversational markers

    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
     betweenstory
    -0.62
    parsedMessage
    -0.62
     CreateTagHelper
    -0.59
     BoxDecoration
    -0.56
    ThroughAttribute
    -0.53
    stateProvider
    -0.53
    styleType
    -0.52
    MLLoader
    -0.51
    ollectionView
    -0.49
    ffions
    -0.48
    POSITIVE LOGITS
     
    1.40
    ) 
    1.02
      
    1.01
    ) 
    0.97
    . 
    0.93
    : 
    0.89
    ~ 
    0.85
    ! 
    0.83
    。 
    0.81
    ? 
    0.81
    Activations Density 0.058%

    No Known Activations