© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7690
    Prev
    Next
    INDEX
    Explanations

    names of artists and their collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     European
    -0.79
    yelitis
    -0.77
    European
    -0.76
     international
    -0.66
     American
    -0.65
     Western
    -0.63
     Asian
    -0.62
     european
    -0.62
     Europe
    -0.60
    astify
    -0.59
    POSITIVE LOGITS
     Италијани
    0.67
    CodedInputStream
    0.57
     дописавши
    0.53
     Core
    0.46
     Мексичка
    0.45
     vägen
    0.44
    LabelTagHelper
    0.44
    客房
    0.43
    retweeted
    0.43
     Nor
    0.43
    Activations Density 0.099%

    No Known Activations