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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4697
    Prev
    Next
    INDEX
    Explanations

    references to software installation and file management within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *)__
    -0.61
     SwitchCompat
    -0.54
    estia
    -0.49
    tear
    -0.49
    ้ง
    -0.46
    encodeWith
    -0.45
    imea
    -0.45
    AccessorTable
    -0.45
    付
    -0.45
    ≦)
    -0.44
    POSITIVE LOGITS
    aarrggbb
    0.76
    DockStyle
    0.65
    RRect
    0.62
    ั้ง
    0.54
     starboard
    0.54
    AxisAlignment
    0.53
    arote
    0.52
     صوتيه
    0.52
    guten
    0.51
    новништво
    0.51
    Activations Density 0.805%

    No Known Activations