© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8567
    Prev
    Next
    INDEX
    Explanations

    elements related to software assembly attributes and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    body
    -0.60
     body
    -0.59
    ::__
    -0.53
    Body
    -0.53
    клопе
    -0.52
     totalSupply
    -0.51
    SerializedSize
    -0.51
     Body
    -0.51
    ClientSize
    -0.50
    actéristique
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.70
     tongues
    0.66
    jspx
    0.64
     tongue
    0.61
    nappropriate
    0.60
    tongue
    0.56
     فريبيس
    0.56
     Forse
    0.54
     arşivlendi
    0.53
    BagConstraints
    0.51
    Activations Density 2.479%

    No Known Activations