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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.44
     exhibition
    -0.42
     scaled
    -0.42
     Fed
    -0.41
     dark
    -0.41
     Adj
    -0.41
     Peer
    -0.41
     drill
    -0.40
     stră
    -0.40
    CreateModel
    -0.40
    POSITIVE LOGITS
    valueOf
    0.66
     valueOf
    0.53
    parseInt
    0.49
    лтемелер
    0.48
     estekak
    0.45
    Personensuche
    0.44
     ujednoznacz
    0.43
    ValueOf
    0.42
     يتيمه
    0.40
    OrWhiteSpace
    0.38
    Activations Density 0.182%

    No Known Activations