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. 4-GEMMASCOPE-RES-16K
    6. 10637
    Prev
    Next
    INDEX
    Explanations

    annotations related to serialization in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.68
     resourceCulture
    -0.66
    Comté
    -0.64
     ocu
    -0.63
    ElementException
    -0.59
    DataSetChanged
    -0.58
    Cyfeiriadau
    -0.58
    ++)
    
    -0.58
    ودي
    -0.56
    peq
    -0.55
    POSITIVE LOGITS
    شهاد
    0.70
    AddTagHelper
    0.66
    󠁢
    0.64
     rowspan
    0.61
    addPreferredGap
    0.61
     InputDecoration
    0.59
    awarkan
    0.59
    اسم
    0.58
    SourceChecksum
    0.58
    texttt
    0.57
    Activations Density 0.095%

    No Known Activations