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. 25-GEMMASCOPE-RES-16K
    6. 8430
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the degree or extent of something

    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
     quoque
    -0.63
    qrst
    -0.58
     väga
    -0.56
     siis
    -0.54
    fjspx
    -0.54
     Référence
    -0.53
    atrices
    -0.52
     quæ
    -0.51
     enää
    -0.50
    ITHER
    -0.49
    POSITIVE LOGITS
     frankly
    0.84
     literally
    0.80
     possibly
    0.75
    literally
    0.72
    ly
    0.70
    possibly
    0.69
     Literally
    0.67
     Possibly
    0.62
     awhile
    0.62
     honestly
    0.62
    Activations Density 0.082%

    No Known Activations