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. 3-GEMMASCOPE-RES-16K
    6. 6209
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical values related to resource parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.77
    ագրություններ
    -0.65
     espagnole
    -0.59
    ьаж
    -0.56
    adaptiveStyles
    -0.56
     MutableLiveData
    -0.54
     ddelweddau
    -0.53
     faſt
    -0.52
     ashore
    -0.52
     subcontra
    -0.51
    POSITIVE LOGITS
    Datuak
    0.78
    CloseOperation
    0.69
    WEBPACK
    0.60
    URLException
    0.60
    MLLoader
    0.59
    yntaxException
    0.58
    Pyx
    0.58
    onViewCreated
    0.56
    XMLSchema
    0.55
    enumerable
    0.54
    Activations Density 0.293%

    No Known Activations