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. 12-GEMMASCOPE-RES-16K
    6. 9677
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical operations involving factors and multiples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.78
    MemoryWarning
    -0.73
     صوتيه
    -0.70
     '\\;'
    -0.67
     سكانية
    -0.66
    HomeAsUpEnabled
    -0.66
     дописавши
    -0.66
     linkovi
    -0.65
     tartalomajánló
    -0.65
     ivelany
    -0.64
    POSITIVE LOGITS
    spreis
    0.44
    zzleHttp
    0.43
     priori
    0.43
    ToReturn
    0.42
     fly
    0.42
    EIF
    0.41
    ToRead
    0.41
     án
    0.41
    ?
    0.41
    EDEFAULT
    0.40
    Activations Density 1.487%

    No Known Activations