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. 41-GEMMASCOPE-RES-16K
    6. 7286
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to problem-solving, particularly in programming or technical contexts

    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
     transfieras
    -0.40
    AddTagHelper
    -0.39
    CopyWith
    -0.37
    tanleria
    -0.36
     więc
    -0.35
    osoever
    -0.35
    それにしても
    -0.35
    hability
    -0.35
     mères
    -0.33
     wenigstens
    -0.32
    POSITIVE LOGITS
     yes
    2.73
     Yes
    2.53
    Yes
    2.41
     YES
    2.16
    yes
    2.16
    YES
    1.93
    是的
    1.51
     yep
    1.47
     sì
    1.41
     yeah
    1.40
    Activations Density 0.556%

    No Known Activations