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. 15-GEMMASCOPE-RES-16K
    6. 8714
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving degrees, dimensions, and ranks in algebraic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.48
     th
    -0.48
    Th
    -0.46
    ang
    -0.46
    ake
    -0.45
    ług
    -0.44
    </em>
    -0.43
     early
    -0.42
    ​
    -0.42
    anga
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    1.08
    aarrggbb
    1.06
    ImageContext
    1.01
    AddTagHelper
    0.94
    WriteTagHelper
    0.88
    ChildScrollView
    0.88
    AndEndTag
    0.86
    exitRule
    0.79
     civiles
    0.78
     épis
    0.77
    Activations Density 0.723%

    No Known Activations