© 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. 3-GEMMASCOPE-RES-16K
    11. 8035
    Prev
    Next
    INDEX
    Explanations

    references to specific programming classes and methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.73
     Duda
    -0.71
     Chry
    -0.67
     Oke
    -0.67
    er
    -0.64
     Boud
    -0.61
    Oke
    -0.59
     poire
    -0.57
     Haring
    -0.56
    perity
    -0.55
    POSITIVE LOGITS
    NS
    2.30
    ns
    2.12
     NS
    2.02
     ns
    1.98
    ans
    1.45
     Ans
    1.37
    ANS
    1.35
     Ns
    1.34
    ENS
    1.32
    ens
    1.31
    Activations Density 0.146%

    No Known Activations