© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6787
    Prev
    Next
    INDEX
    Explanations

    syntax and formatting related to mathematical expressions or programming code

    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
    INSEE
    -0.60
     ویکی‌پدیای
    -0.48
    selectedIndex
    -0.44
     []),
    -0.43
    ([]);
    -0.42
     />';
    -0.42
    粋
    -0.42
     "'";
    -0.42
     lì
    -0.42
    ApiModelProperty
    -0.41
    POSITIVE LOGITS
    httphttps
    0.76
    DockStyle
    0.74
    
    0.74
    SBATCH
    0.73
    BeginContext
    0.69
     كومونز
    0.68
    esgue
    0.64
    tvguidetime
    0.64
     AppColors
    0.64
     referrerpolicy
    0.64
    Activations Density 0.633%

    No Known Activations