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. 857
    Prev
    Next
    INDEX
    Explanations

    code snippets or structures related to thread management and locking mechanisms

    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
    ]")]
    -0.75
    出版年
    -0.68
     untitled
    -0.63
    الحياه
    -0.60
    ).__
    -0.60
     }}$}
    -0.60
    存于互联网档案馆
    -0.59
    enumii
    -0.59
     """
    
    -0.59
    onBackPressed
    -0.59
    POSITIVE LOGITS
    fromnode
    0.59
    webElement
    0.51
    IntoConstraints
    0.49
     Osna
    0.46
    IonicModule
    0.45
    Hentet
    0.45
    醐
    0.43
    蒙
    0.41
     betweenstory
    0.41
     Dernière
    0.41
    Activations Density 0.213%

    No Known Activations