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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11687
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to morphisms, projections, and algebraic varieties

    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
     يتيمه
    -0.56
    TemporalType
    -0.55
    Diwedd
    -0.55
     للاسماء
    -0.54
     Meksiku
    -0.53
     насељу
    -0.53
    SBATCH
    -0.53
    MemoryWarning
    -0.52
     invokingState
    -0.51
     AspNetCore
    -0.50
    POSITIVE LOGITS
     AutoMapper
    0.60
     mapping
    0.43
    Mapping
    0.40
     Mapping
    0.37
     transformation
    0.37
     transforms
    0.36
     poveznice
    0.35
    Transforms
    0.35
     transform
    0.35
    mapping
    0.34
    Activations Density 1.479%

    No Known Activations