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. 1-GEMMASCOPE-RES-16K
    6. 13798
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software installation and package management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.82
    ########.
    -0.71
    
    -0.66
    帖最后由
    -0.65
    saraba
    -0.59
     CentOS
    -0.55
    unistd
    -0.54
    脚注の使い方
    -0.53
    Personensuche
    -0.51
    sudo
    -0.51
    POSITIVE LOGITS
     StatelessWidget
    0.59
     betweenstory
    0.58
    OrBuilder
    0.57
     déchir
    0.54
     &___
    0.53
    jalá
    0.53
    ApiModel
    0.53
     vôtre
    0.51
     chi̍t
    0.51
    Poloha
    0.50
    Activations Density 2.179%

    No Known Activations