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

    Neuronpedia

    APICircuit 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. 7718
    Prev
    Next
    INDEX
    Explanations

    code snippets and definitions related to programming functions, particularly for manipulating data formats such as JSON and XML

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

    Writing to output streams or files

    np_acts-logits-general · gemini-2.0-flash

    writing to output

    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
     CommandType
    -0.60
    BitmapFactory
    -0.58
     Arrival
    -0.57
     Received
    -0.57
    imread
    -0.57
     TestBed
    -0.56
     RECEIVED
    -0.56
     received
    -0.56
     auditions
    -0.56
    Brought
    -0.55
    POSITIVE LOGITS
     output
    1.59
     Output
    1.51
    output
    1.40
    Output
    1.34
    输出
    1.30
    OutputStream
    1.27
     OUTPUT
    1.27
     writing
    1.21
    OUTPUT
    1.20
     输出
    1.19
    Activations Density 0.497%

    No Known Activations