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. 31-GEMMASCOPE-RES-16K
    6. 3089
    Prev
    Next
    INDEX
    Explanations

    specific names and phrases that pertain to authorship and contributions in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Chinese and Korean names, particularly in author attribution and cast listing sections.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungszeit
    -0.39
     quæ
    -0.39
     WaitForSeconds
    -0.38
    MEMORANDUM
    -0.37
    ToBounds
    -0.36
     desertcart
    -0.36
    แผ
    -0.36
     špec
    -0.36
     suerte
    -0.33
     paella
    -0.33
    POSITIVE LOGITS
     Zhang
    0.74
     Xu
    0.65
     Chen
    0.63
     Liu
    0.62
     Wang
    0.61
    Zhang
    0.60
     Zhao
    0.57
    Xu
    0.57
     Wu
    0.57
     Lin
    0.57
    Activations Density 0.140%

    No Known Activations