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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 4215
    Prev
    Next
    INDEX
    Explanations

    code structure and control flow components such as brackets and keywords

    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
     correctes
    -0.55
    তথ্যসূত্র
    -0.55
     eens
    -0.52
     plainte
    -0.52
    ricing
    -0.51
    lyon
    -0.47
    nému
    -0.47
    estino
    -0.47
     okazji
    -0.47
    nessed
    -0.46
    POSITIVE LOGITS
    protoimpl
    0.61
    InvalidProtocol
    0.60
    WindowConstants
    0.59
    UnknownFields
    0.59
    MessageTagHelper
    0.57
     Normdatei
    0.56
     متعلقه
    0.56
    GEBURTSDATUM
    0.54
    \{\\
    0.53
    Зноскі
    0.53
    Activations Density 0.083%

    No Known Activations