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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14931
    Prev
    Next
    INDEX
    Explanations

    syntactic and structural patterns in mathematical or programming contexts

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

    numbers

    np_acts-logits-general · gemini-2.0-flash

    six

    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
     terecht
    -0.59
    Itoa
    -0.52
     prisonniers
    -0.51
    HttpPost
    -0.49
    grà
    -0.49
     vôtre
    -0.48
     travailleurs
    -0.44
    ingual
    -0.44
     Rumuni
    -0.44
     ativos
    -0.44
    POSITIVE LOGITS
    6
    1.02
     sixth
    0.81
     Six
    0.81
     Sixty
    0.80
     six
    0.76
     CreateTagHelper
    0.74
    Sixty
    0.74
    six
    0.74
     sixty
    0.74
     SIX
    0.73
    Activations Density 0.457%

    No Known Activations