Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6407
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to graph traversal and recursive functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hmot
    -0.48
    timg
    -0.41
     écl
    -0.41
     Blank
    -0.41
    下载附件
    -0.40
    ikas
    -0.39
    TRUNC
    -0.39
    Defaults
    -0.38
    掩
    -0.38
     éclat
    -0.38
    POSITIVE LOGITS
     dfs
    0.85
    stdc
    0.84
     Majefty
    0.80
    DFS
    0.78
    etCode
    0.76
     DFS
    0.76
    BFS
    0.76
    dfs
    0.76
     bfs
    0.73
     useSelector
    0.72
    Activations Density 0.686%

    No Known Activations