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. 22-GEMMASCOPE-RES-16K
    6. 10941
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and phrases related to biochemical substances and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "fluid", "serum", or "medium" in cell culture

    np_acts-logits-general · gemini-2.0-flash

    fetal calf/bovine, working fluid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.76
     autorytatywna
    -0.69
    Derbyniad
    -0.67
     Wiktionnaire
    -0.64
     StatefulWidget
    -0.63
    XmlEnum
    -0.61
    WithIOException
    -0.60
    })();
    
    -0.58
     propOrder
    -0.57
    UnusedPrivate
    -0.56
    POSITIVE LOGITS
    ioutil
    0.64
     يتيمه
    0.62
    WriteAttribute
    0.60
    TypedDataSet
    0.59
    InputTagHelper
    0.58
    Portail
    0.58
    ależy
    0.57
    ImageField
    0.55
    териалы
    0.53
     MainAxisSize
    0.52
    Activations Density 1.774%

    No Known Activations