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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 7024
    Prev
    Next
    INDEX
    Explanations

    complex mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.71
    Brainz
    -0.66
    ukone
    -0.64
     otomatig
    -0.61
    RegressionTest
    -0.59
     createSprite
    -0.58
    tomans
    -0.54
    [];
    
    -0.52
    ministrazione
    -0.52
     منهم
    -0.52
    POSITIVE LOGITS
     للمعارف
    0.84
    存于互联网档案馆
    0.65
    ⓧ
    0.63
    SharedDtor
    0.62
    styleType
    0.58
     Amic
    0.56
     Athene
    0.54
    ffffffff
    0.54
     väli
    0.54
     تانيه
    0.53
    Activations Density 0.113%

    No Known Activations