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. 12789
    Prev
    Next
    INDEX
    Explanations

    JavaScript code related to variable and constant declarations

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

    Code-related keywords such as "const", "var", "{", and "fs"

    np_acts-logits-general · gemini-2.0-flash

    variable declarations and code keywords

    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
     према
    -0.63
    gonic
    -0.61
    lapsingToolbar
    -0.59
    脚注の使い方
    -0.59
    DataAnnotations
    -0.58
    twimg
    -0.56
    SequentialGroup
    -0.56
    ])]
    -0.54
     ((*
    -0.53
     kram
    -0.53
    POSITIVE LOGITS
     fs
    0.62
     express
    0.56
    URLException
    0.55
     {
    0.52
    assert
    0.52
    fs
    0.50
     assert
    0.47
     {
    
    0.47
    expect
    0.47
     moment
    0.46
    Activations Density 0.076%

    No Known Activations