© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6952
    Prev
    Next
    INDEX
    Explanations

    structured data elements in a document such as tags, parameters, and associated values

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

    HTML tags/Theorem statements

    np_acts-logits-general · gemini-2.0-flash

    markup and citations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     propias
    -0.46
     humaines
    -0.45
     útiles
    -0.45
     artesanales
    -0.44
     extranjeros
    -0.42
     verdaderas
    -0.42
     humaine
    -0.41
    CodeAttribute
    -0.41
     humanas
    -0.40
     auténtica
    -0.40
    POSITIVE LOGITS
     nakalista
    0.72
    expandindo
    0.58
    ngdoc
    0.57
    findpost
    0.56
     HasFactory
    0.56
    AndEndTag
    0.55
    曖昧さ回避
    0.54
    oneofs
    0.54
     decl
    0.53
    tonode
    0.52
    Activations Density 2.975%

    No Known Activations