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. 13-GEMMASCOPE-RES-16K
    6. 9380
    Prev
    Next
    INDEX
    Explanations

    references to "novels" and "artificial" concepts or intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lic
    -0.71
     Kabel
    -0.68
     kele
    -0.67
    tas
    -0.67
     tas
    -0.66
    ,\
    -0.66
    former
    -0.63
     my
    -0.63
    لمين
    -0.60
    <u>
    -0.60
    POSITIVE LOGITS
     GenerationType
    1.05
     nahilalakip
    1.02
     Мексичка
    0.98
     ◦
    0.96
     spacy
    0.95
    ukone
    0.92
     ་་
    0.91
     Arno
    0.90
    gdx
    0.90
    "}")
    0.89
    Activations Density 0.338%

    No Known Activations