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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7383
    Prev
    Next
    INDEX
    Explanations

    color specifications in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.88
    Personensuche
    -0.76
     Италијани
    -0.71
    ParallelGroup
    -0.65
    SharedDtor
    -0.64
     typelib
    -0.64
    GOTREF
    -0.64
    DeleteBehavior
    -0.64
    ftagPool
    -0.63
    MEMORANDUM
    -0.63
    POSITIVE LOGITS
    tvguidetime
    0.70
    Xna
    0.51
     wikipagina
    0.50
    enumi
    0.47
    stretchr
    0.46
     chariots
    0.45
    ographer
    0.44
    BeginContext
    0.44
    SqlClient
    0.43
    Skocz
    0.42
    Activations Density 0.109%

    No Known Activations