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. 11-GEMMASCOPE-RES-16K
    6. 6810
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to quantitative measurements and analysis, especially in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onActivityResult
    -0.76
     appelez
    -0.75
    -------------</
    -0.75
    ValueGeneration
    -0.75
     Administrativna
    -0.72
    テンツ
    -0.71
    DoubleQuotes
    -0.71
    >--}}
    -0.69
     للاسماء
    -0.69
    QMetaType
    -0.69
    POSITIVE LOGITS
     face
    0.47
    errat
    0.44
    旁
    0.44
     ligiloj
    0.44
     want
    0.43
    bootstrapcdn
    0.42
    ddot
    0.40
     ponta
    0.40
    \\
    0.40
     κό
    0.39
    Activations Density 0.615%

    No Known Activations