© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 48
    Prev
    Next
    INDEX
    Explanations

    the word "still" in various contexts

    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
    CrossRef
    -0.85
     verkligen
    -0.75
    eraard
    -0.74
    already
    -0.74
    出版年
    -0.73
    sejarah
    -0.70
    SerializedSize
    -0.68
     whiche
    -0.68
     lisäksi
    -0.68
    epiece
    -0.68
    POSITIVE LOGITS
     yet
    0.75
     remains
    0.68
     belum
    0.66
    born
    0.64
     retains
    0.63
    Yet
    0.63
     Yet
    0.59
    しも
    0.58
     remain
    0.57
     Normdatei
    0.57
    Activations Density 0.095%

    No Known Activations