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. 13778
    Prev
    Next
    INDEX
    Explanations

    numeric references or identifiers related to data or studies

    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
     
    -0.75
    }$​
    -0.52
     "
    -0.50
    कारी
    -0.50
     “
    -0.50
    들에게
    -0.49
    mbic
    -0.49
    ]');
    -0.48
    soi
    -0.48
    HasValue
    -0.47
    POSITIVE LOGITS
     مشين
    1.17
    audiovisuel
    1.08
     ​​
    0.93
    出版年
    0.93
    cookieParser
    0.91
     Rptr
    0.90
    randomUUID
    0.90
    WriteTagHelper
    0.87
     ويكيميديا
    0.85
    CDCl
    0.85
    Activations Density 0.590%

    No Known Activations