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. 10006
    Prev
    Next
    INDEX
    Explanations

    discussions of consequences and repercussions in various contexts

    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
     tartalomajánló
    -0.65
    omock
    -0.63
     ویکی‌پدیا
    -0.57
     Есть
    -0.55
    seling
    -0.55
    AddRef
    -0.52
     protoimpl
    -0.52
    zeln
    -0.51
    hebt
    -0.51
     InputDecoration
    -0.49
    POSITIVE LOGITS
     consequences
    1.56
     consequence
    1.38
    Consequences
    1.33
     Consequences
    1.33
     repercussions
    1.22
     conseguenze
    1.20
     conséquences
    1.19
     consecuencias
    1.15
    effects
    1.14
     effects
    1.11
    Activations Density 0.363%

    No Known Activations