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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14047
    Prev
    Next
    INDEX
    Explanations

    contextual phrases related to conditions and the extent of scenarios or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁿
    -0.64
     arşivlendi
    -0.61
    فحة
    -0.55
    ejec
    -0.46
    ranath
    -0.46
    ſt
    -0.46
    XmlType
    -0.45
    UniformLocation
    -0.43
     οποία
    -0.43
     Shores
    -0.43
    POSITIVE LOGITS
    OGND
    0.56
     ***!
    0.55
     disponibilités
    0.54
     tartalomajánló
    0.53
     CreateTagHelper
    0.53
    ValueStyle
    0.53
    kwür
    0.52
     ComVisible
    0.51
     OFDb
    0.50
     ModelExpression
    0.47
    Activations Density 1.272%

    No Known Activations