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. 65860
    Prev
    Next
    INDEX
    Explanations

    structured information related to articles and their metadata

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

    syndication feed articles

    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
     BorderSide
    -0.45
     zwią
    -0.40
    RenderAtEndOf
    -0.35
    minecraftforge
    -0.34
     suivante
    -0.34
     latar
    -0.33
    especie
    -0.33
     skú
    -0.31
     pesado
    -0.31
    Poznám
    -0.31
    POSITIVE LOGITS
    
    0.79
    Portail
    0.62
    igslist
    0.57
    webElementXpaths
    0.56
    ManagedBean
    0.55
     PeEnEo
    0.54
     allAfrica
    0.53
    onViewCreated
    0.52
    elemField
    0.50
     Савезне
    0.50
    Activations Density 0.184%

    No Known Activations