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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 52938
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "abc" within code or technical documentation, particularly related to JetBrains products

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

    abc and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -1.12
    PullParser
    -0.88
    interopRequire
    -0.86
    MessageTagHelper
    -0.85
     <=",
    -0.82
     AspNetCore
    -0.81
     >=",
    -0.81
     AssemblyVersion
    -0.79
    posedge
    -0.79
    verwijspagina
    -0.78
    POSITIVE LOGITS
     abc
    1.56
    abc
    1.23
     ABC
    1.00
    ABC
    0.95
    Abc
    0.92
    ABCD
    0.69
     ABCD
    0.58
    abcd
    0.54
     Schweitzer
    0.52
    abcdef
    0.51
    Activations Density 0.003%

    No Known Activations