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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6233
    Prev
    Next
    INDEX
    Explanations

    references to specific amino acid sequences and their classifications

    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
     branca
    -0.61
     interception
    -0.57
     Coup
    -0.57
    RequestMethod
    -0.56
     obstruction
    -0.56
    writeObject
    -0.56
     Hahn
    -0.56
     IOException
    -0.52
     Aldrich
    -0.52
     quanto
    -0.52
    POSITIVE LOGITS
    al
    2.45
    AL
    1.48
    alna
    1.09
    alni
    1.09
    alny
    0.96
    almente
    0.91
    alne
    0.77
    alva
    0.77
    alaya
    0.75
    ary
    0.74
    Activations Density 0.195%

    No Known Activations