Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5795
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or beliefs

    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
     виправивши
    -0.81
    StructEnd
    -0.73
     Wiktionnaire
    -0.72
    曖昧さ回避
    -0.66
    AndEndTag
    -0.66
    IsContent
    -0.65
     الحره
    -0.65
    GEBURTSDATUM
    -0.62
     跳转至
    -0.61
    aarrggbb
    -0.60
    POSITIVE LOGITS
     doubt
    0.79
    doubt
    0.62
     wouldn
    0.61
     doute
    0.57
     seriously
    0.57
     guarantee
    0.57
     doubts
    0.56
     shudder
    0.56
     сом
    0.55
     doubtful
    0.55
    Activations Density 0.242%

    No Known Activations