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. 23-GEMMASCOPE-RES-16K
    6. 4878
    Prev
    Next
    INDEX
    Explanations

    phrases that describe residential properties and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.67
    Pyx
    -0.64
    ArgsConstructor
    -0.63
     חיצוניים
    -0.62
     Buildings
    -0.59
     apartments
    -0.59
    Sklici
    -0.58
     EconPapers
    -0.57
     Apartments
    -0.56
    Buildings
    -0.55
    POSITIVE LOGITS
     corner
    0.69
     end
    0.59
     single
    0.59
     endregion
    0.58
     CORNER
    0.58
     ramb
    0.58
     rancher
    0.58
    posedge
    0.57
     ranch
    0.56
     town
    0.56
    Activations Density 0.078%

    No Known Activations