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. 39-GEMMASCOPE-RES-16K
    6. 4307
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles or relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aktery
    -0.39
    parsedMessage
    -0.38
    PROTOBUF
    -0.37
     Consumo
    -0.37
     refaire
    -0.34
     chịu
    -0.34
     wikipagina
    -0.33
    arraycopy
    -0.33
     maîtrise
    -0.33
     soin
    -0.32
    POSITIVE LOGITS
     launching
    1.02
     stepping
    0.99
     jumping
    0.94
     spring
    0.92
     catalyst
    0.91
     starting
    0.90
     platform
    0.85
     impetus
    0.84
    stepping
    0.84
    spring
    0.81
    Activations Density 0.500%

    No Known Activations