© 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. 1-GEMMASCOPE-RES-16K
    11. 3901
    Prev
    Next
    INDEX
    Explanations

    terms related to semi-variable or semi-structured concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     swing
    -1.15
    swing
    -1.06
     Swing
    -0.96
    Swing
    -0.93
     swinging
    -0.91
     swings
    -0.81
     swung
    -0.76
    ագրություններ
    -0.71
    ANTLR
    -0.68
     ujednoznacz
    -0.65
    POSITIVE LOGITS
     của
    1.36
    ของ
    0.93
     av
    0.74
     ของ
    0.69
     של
    0.69
     semi
    0.67
    Semi
    0.64
    ủa
    0.64
     του
    0.63
    dirname
    0.59
    Activations Density 0.047%

    No Known Activations