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. 2813
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations related to a specific context or narrative

    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
     відо
    -0.33
     empty
    -0.32
     etk
    -0.32
     soldadura
    -0.32
     есть
    -0.31
    Còn
    -0.30
     cremallera
    -0.28
    żli
    -0.28
     INCRE
    -0.28
     ziua
    -0.28
    POSITIVE LOGITS
     singh
    0.68
     Trip
    0.68
    Gupta
    0.68
    Sharma
    0.66
     Sax
    0.66
     Gupta
    0.66
     Sharma
    0.65
     Sing
    0.65
    Sax
    0.65
     Arora
    0.65
    Activations Density 0.312%

    No Known Activations