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. 22-GEMMASCOPE-RES-16K
    6. 6045
    Prev
    Next
    INDEX
    Explanations

    technical terms related to installation and configuration processes

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

    Programming-related terms and contexts

    np_acts-logits-general · gemini-2.0-flash

    software and system commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelpers
    -0.58
     chi̍t
    -0.56
    +#+#
    -0.55
    AddAttribute
    -0.54
     berço
    -0.53
     hänen
    -0.50
    \}\\
    -0.50
    ---*/
    -0.50
    -------------</
    -0.50
    WriteLiteral
    -0.49
    POSITIVE LOGITS
     Microsoft
    1.27
     Google
    1.17
     Windows
    1.11
     Adobe
    1.11
    Microsoft
    0.97
     WordPress
    0.95
     google
    0.90
     Android
    0.88
     MATLAB
    0.86
     Photoshop
    0.86
    Activations Density 1.782%

    No Known Activations