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. 7249
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to percentages and quantities

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

    quantities and percentages

    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
    AndEndTag
    -0.57
    tagHelperRunner
    -0.57
     BoxFit
    -0.55
     GenerationType
    -0.51
    脚注の使い方
    -0.49
    contentLoaded
    -0.48
    
    -0.48
     PTC
    -0.47
     ProtoMessage
    -0.47
     HasFactory
    -0.47
    POSITIVE LOGITS
     more
    0.42
     extra
    0.40
     additional
    0.36
     hoeveel
    0.35
     dem
    0.34
     real
    0.34
    writeObject
    0.32
    Sprintf
    0.32
     Will
    0.31
     wireType
    0.31
    Activations Density 0.166%

    No Known Activations