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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 28124
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.58
    +#+#
    -0.57
     ſtand
    -0.57
    principalColumn
    -0.52
    pgterms
    -0.50
     juſ
    -0.50
     MainAxisSize
    -0.49
    Życiorys
    -0.48
    adaptiveStyles
    -0.47
     pleaſure
    -0.47
    POSITIVE LOGITS
    LabelTagHelper
    0.53
    FieldDescriptor
    0.41
    Spoljašnje
    0.37
     yyr
    0.35
     ModelExpression
    0.35
    ต่างๆ
    0.34
    ApiOperation
    0.34
    entlichen
    0.34
     mał
    0.33
    FormGroup
    0.33
    Activations Density 0.002%

    No Known Activations