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. 15453
    Prev
    Next
    INDEX
    Explanations

    references to student achievements and academic competitions

    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
     CreateTagHelper
    -1.05
    AutoScaleMode
    -0.91
     initComponents
    -0.84
    IntoConstraints
    -0.81
     незавершена
    -0.81
     كومونز
    -0.77
    تقاوى
    -0.77
    roffen
    -0.74
    MLLoader
    -0.73
    AndEndTag
    -0.73
    POSITIVE LOGITS
    évaluateur
    0.51
     R
    0.51
    jetunion
    0.45
    ini
    0.45
     espuma
    0.44
     carpenter
    0.44
     فنی
    0.44
     signora
    0.43
     John
    0.43
    iso
    0.41
    Activations Density 0.214%

    No Known Activations