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. 0-GEMMASCOPE-RES-16K
    6. 7705
    Prev
    Next
    INDEX
    Explanations

    references to the delete operation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.72
    帖最后由
    -0.68
     MainAxisSize
    -0.67
     snippetHide
    -0.66
     препратки
    -0.62
     queſta
    -0.61
    postsleuth
    -0.60
    Skocz
    -0.59
    LikeLiked
    -0.58
    listdir
    -0.57
    POSITIVE LOGITS
     complete
    0.63
    delete
    0.60
    complete
    0.54
     confronted
    0.52
    Complete
    0.45
    COMPLETE
    0.44
     Complete
    0.44
     theirs
    0.43
     comparative
    0.41
     comprehensive
    0.40
    Activations Density 0.213%

    No Known Activations