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. 77132
    Prev
    Next
    INDEX
    Explanations

    numerical values and the contexts in which they appear

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

    numbers and units

    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
     rasanya
    -0.36
     soigneusement
    -0.36
     excelencia
    -0.34
     gewöhnlich
    -0.33
     rarement
    -0.33
     pasaj
    -0.33
     verdad
    -0.32
     urgencia
    -0.32
     Reisen
    -0.31
     costumbres
    -0.31
    POSITIVE LOGITS
    AddTagHelper
    0.63
    Numerade
    0.61
    tvguidetime
    0.61
    +#+#
    0.60
     propOrder
    0.58
     дописавши
    0.58
    TagMode
    0.58
    setObjectName
    0.58
    ngdoc
    0.57
     nahilalakip
    0.56
    Activations Density 0.225%

    No Known Activations