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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3869
    Prev
    Next
    INDEX
    Explanations

    conditional statements and control flow structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -1.02
    CloseOperation
    -0.85
    +#+#
    -0.83
     فريبيس
    -0.82
     vectoriales
    -0.79
     كومونز
    -0.78
     متعلقه
    -0.78
    AddTagHelper
    -0.76
    ArgsConstructor
    -0.76
    enumi
    -0.74
    POSITIVE LOGITS
    GEBURTSDATUM
    0.59
    tvguidetime
    0.57
    tes
    0.46
    te
    0.45
     CURIAM
    0.43
    }^{(\
    0.43
    CELLANEOUS
    0.42
    <bos>
    0.42
     $\
    0.41
    WebElementEntity
    0.41
    Activations Density 0.936%

    No Known Activations