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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11736
    Prev
    Next
    INDEX
    Explanations

    numeric representations and scientific notation within a mathematical or statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    FormTagHelper
    -0.63
     يتيمه
    -0.60
    PerformLayout
    -0.58
    IntoConstraints
    -0.55
     فريبيس
    -0.54
    StoryboardSegue
    -0.52
     tää
    -0.52
    tagHelperRunner
    -0.52
     financiera
    -0.50
     fieldNum
    -0.50
    POSITIVE LOGITS
    adaptiveStyles
    0.39
     The
    0.39
    The
    0.37
     âge
    0.32
    Pe
    0.32
    }],
    
    0.31
     Edad
    0.31
     profili
    0.31
    xfb
    0.31
     verhe
    0.30
    Activations Density 0.124%

    No Known Activations