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. 10-GEMMASCOPE-RES-16K
    6. 15888
    Prev
    Next
    INDEX
    Explanations

    technical terms and configurations related to networking and server management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nelse
    -0.60
     StatefulWidget
    -0.60
    ỡng
    -0.55
    cstring
    -0.54
    SuspendLayout
    -0.53
    atri
    -0.52
    Race
    -0.51
     bụ
    -0.50
     race
    -0.50
    Források
    -0.50
    POSITIVE LOGITS
    端口
    0.68
     apost
    0.59
     AspNetCore
    0.58
    .*")]
    0.58
    ポート
    0.57
     port
    0.55
     Port
    0.55
    IVEREF
    0.54
    Port
    0.52
    RTEE
    0.52
    Activations Density 0.182%

    No Known Activations