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. 12844
    Prev
    Next
    INDEX
    Explanations

    terms related to technical parameters and conditions in statistical 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
    //
    -0.50
    artifactId
    -0.50
    شهاد
    -0.50
    ORIA
    -0.47
    hoeddwyd
    -0.46
    zium
    -0.46
    MockBean
    -0.45
     vira
    -0.45
    áro
    -0.45
    "]);
    
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.64
     referrerpolicy
    0.58
    AndEndTag
    0.58
    blico
    0.57
     الرياضيه
    0.56
    ostante
    0.55
     EClass
    0.54
    HomeAsUp
    0.54
     дописавши
    0.53
     Abonnez
    0.53
    Activations Density 1.737%

    No Known Activations