© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9639
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs, particularly those associated with documentation and support structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xmlns
    -0.79
     ویکی‌پدیای
    -0.74
    bootstrapcdn
    -0.67
    CodeAttribute
    -0.55
    ArgsConstructor
    -0.55
    новништво
    -0.54
     newData
    -0.53
    번
    -0.49
     aéri
    -0.49
     tilla
    -0.48
    POSITIVE LOGITS
    CloseOperation
    0.81
    AddTagHelper
    0.74
     snippetHide
    0.68
    adaptiveStyles
    0.67
     صوتيه
    0.66
     betweenstory
    0.65
    UseVisualStyle
    0.64
    guió
    0.64
     متعلقه
    0.64
    gawa
    0.62
    Activations Density 0.009%

    No Known Activations