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. 19-GEMMASCOPE-RES-16K
    6. 15263
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or qualifications in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.72
    তথ্যসূত্র
    -0.70
    UnsafeEnabled
    -0.67
    PhysRev
    -0.66
     كومونز
    -0.63
    новништво
    -0.59
     kaarangay
    -0.59
    umenten
    -0.57
     CreateTagHelper
    -0.55
    umis
    -0.55
    POSITIVE LOGITS
     anyway
    3.88
     anyways
    3.26
    anyway
    3.15
     anyhow
    2.83
     Anyway
    2.80
    Anyway
    2.77
     Anyways
    2.19
    Anyways
    2.07
    Anyhow
    1.98
     ohnehin
    1.87
    Activations Density 0.416%

    No Known Activations