Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12636
    Prev
    Next
    INDEX
    Explanations

    data structures and function syntax in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    program code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.77
     Мексичка
    -0.74
    Vidite
    -0.71
    ^(@)
    -0.71
     المعيارى
    -0.68
     CreateTagHelper
    -0.67
     समीक्षक
    -0.66
    URLException
    -0.66
     myſelf
    -0.65
    fromnode
    -0.65
    POSITIVE LOGITS
    MultipartFile
    0.50
    WebControls
    0.47
    SizeF
    0.47
    imageio
    0.46
    gdx
    0.45
    ombie
    0.45
    ResumeLayout
    0.44
    easeOut
    0.44
    AMPLE
    0.41
    runde
    0.41
    Activations Density 0.045%

    No Known Activations