© 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. 2-GEMMASCOPE-RES-16K
    11. 6520
    Prev
    Next
    INDEX
    Explanations

    gerunds or present participles 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     who
    -0.56
    umman
    -0.51
     holding
    -0.51
     whose
    -0.51
     having
    -0.50
     not
    -0.47
     showing
    -0.46
     getting
    -0.45
     being
    -0.45
    orst
    -0.45
    POSITIVE LOGITS
    Going
    1.15
     Taking
    1.14
     Going
    1.13
    Taking
    1.12
     Using
    1.09
    Using
    1.09
    Looking
    1.08
     Looking
    1.05
     Choosing
    1.03
    Seeing
    1.00
    Activations Density 0.206%

    No Known Activations