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. 3758
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating state or condition

    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
     springfox
    -0.63
     sahiptir
    -0.61
     sağlar
    -0.58
     œuvre
    -0.56
    unmodifiable
    -0.54
     melainkan
    -0.54
     الاطلاع
    -0.53
    RegressionTest
    -0.52
     nessuna
    -0.51
     Roskov
    -0.51
    POSITIVE LOGITS
     kinda
    0.98
     kind
    0.92
     suppose
    0.88
     supposed
    0.87
     pretty
    0.81
     gonna
    0.74
     fine
    0.73
     sort
    0.72
     sorta
    0.72
     great
    0.71
    Activations Density 0.515%

    No Known Activations