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. 11-GEMMASCOPE-RES-16K
    6. 13899
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific investigations and their methodologies

    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
    Autoritní
    -0.69
    RegressionTest
    -0.59
     ISNI
    -0.51
    own
    -0.46
     intptr
    -0.44
     AssemblyTitle
    -0.44
    AndEndTag
    -0.43
     Segurança
    -0.43
    stdin
    -0.43
    済
    -0.43
    POSITIVE LOGITS
    AxisAlignment
    0.71
    IndentedString
    0.67
    ioutil
    0.63
    mergeFrom
    0.58
    thâu
    0.57
    Obrázky
    0.57
    conomie
    0.57
    MLLoader
    0.56
    WidgetItem
    0.55
    ::{
    0.55
    Activations Density 0.603%

    No Known Activations