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. 8708
    Prev
    Next
    INDEX
    Explanations

    closing brackets in code syntax

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

    Closing parenthesis, brackets, or braces

    np_acts-logits-general · gemini-2.0-flash

    closing delimiters

    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
     Bom
    -0.59
    WaitGroup
    -0.59
    خواندن
    -0.58
    Obrázky
    -0.58
    *)((
    -0.56
    yarnpkg
    -0.56
     Ballard
    -0.56
    stdc
    -0.55
    يميديا
    -0.55
     varandra
    -0.55
    POSITIVE LOGITS
     مرئيه
    0.67
    GeneratedValue
    0.60
    Huhu
    0.58
    meteor
    0.58
     Roskov
    0.58
    +};
    0.57
    zwischen
    0.57
    Composable
    0.57
    CppCodeGen
    0.56
     Autorisations
    0.56
    Activations Density 0.271%

    No Known Activations