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. 14-GEMMASCOPE-RES-16K
    6. 10506
    Prev
    Next
    INDEX
    Explanations

    programming functions and their structures related to parsing, managing, and manipulating data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nonatomic
    -0.47
    Zaj
    -0.47
     cref
    -0.46
    Bé
    -0.45
    webElementGuid
    -0.45
    Supp
    -0.44
     ||
    
    -0.44
    ')")
    -0.43
    leb
    -0.43
    :</
    -0.43
    POSITIVE LOGITS
    Билгалдахарш
    0.75
    TemporalType
    0.70
    LabelTagHelper
    0.67
    Obrázky
    0.66
     विश्वसनीयता
    0.64
     généraux
    0.64
    XmlAccessType
    0.63
    ########.
    0.61
     ovan
    0.61
    AddTagHelper
    0.61
    Activations Density 0.235%

    No Known Activations