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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15834
    Prev
    Next
    INDEX
    Explanations

    constructs related to coding and function execution in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.96
     мәкал
    -0.70
    GraphicsUnit
    -0.68
    AddTagHelper
    -0.68
     فريبيس
    -0.66
     tartalomajánló
    -0.64
     الحره
    -0.60
    Aktualisiert
    -0.59
    ISupport
    -0.57
     يتيمه
    -0.57
    POSITIVE LOGITS
    GEBURTSDATUM
    0.37
    fjspx
    0.37
    InjectMocks
    0.36
     EClass
    0.36
    PerformLayout
    0.35
    libft
    0.34
     propOrder
    0.34
     privat
    0.34
    MessageTagHelper
    0.33
    TableField
    0.32
    Activations Density 0.127%

    No Known Activations