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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15622
    Prev
    Next
    INDEX
    Explanations

    elements related to formatting and structure within the text

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

    HTML tags and formatting

    np_acts-logits-general · gemini-2.0-flash

    **part of tribute**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
    mergeFrom
    -0.81
    SizeMode
    -0.76
     typelib
    -0.75
     ComVisible
    -0.74
    +#+
    -0.73
    tonsoft
    -0.70
     صوتيه
    -0.70
    IndentedString
    -0.69
    WriteTagHelper
    -0.69
    POSITIVE LOGITS
    ↵↵
    0.87
    ↵↵↵
    0.81
    <eos>
    0.79
    ↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵
    0.66
    ↵↵↵↵↵
    0.65
    ↵↵↵↵↵↵↵↵↵
    0.63
    ↵↵↵↵↵↵
    0.62
    ↵↵↵↵↵↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵↵↵↵↵
    0.56
    Activations Density 0.136%

    No Known Activations