© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3776
    Prev
    Next
    INDEX
    Explanations

    references to holes, particularly in different contexts and sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.64
    aarrggbb
    -0.60
     beginnetje
    -0.58
    AsUp
    -0.56
    PROTOBUF
    -0.55
    TestFixture
    -0.52
     abz
    -0.51
    もしれません
    -0.51
     Barbier
    -0.51
    ManagedBean
    -0.50
    POSITIVE LOGITS
     hole
    2.96
     holes
    2.88
     Hole
    2.80
    Hole
    2.69
     Holes
    2.69
    hole
    2.68
     HOLE
    2.53
    holes
    2.45
    Holes
    2.30
    HOLE
    2.26
    Activations Density 0.079%

    No Known Activations