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. 21-GEMMASCOPE-RES-16K
    6. 2252
    Prev
    Next
    INDEX
    Explanations

    syntax or structural elements related to programming code, particularly Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.53
    TagHelper
    -0.53
    Климат
    -0.52
    ார்
    -0.52
    esez
    -0.51
     resourceCulture
    -0.50
     disambiguazione
    -0.49
     שוליים
    -0.48
     descar
    -0.47
    انجليز
    -0.46
    POSITIVE LOGITS
    getClass
    0.66
    noinspection
    0.61
    equals
    0.61
    antMatchers
    0.61
    yntaxException
    0.60
    hashCode
    0.58
    </caption>
    0.58
    /******/
    0.57
     getClass
    0.57
    >");
    0.56
    Activations Density 0.100%

    No Known Activations