© 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. 25-GEMMASCOPE-RES-16K
    11. 351
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" in different contexts

    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
    ,
    -0.70
     and
    -0.59
    ,?
    -0.55
    ,}
    -0.55
    e
    -0.54
    however
    -0.53
    i
    -0.50
    <bos>
    -0.48
    l
    -0.48
    n
    -0.47
    POSITIVE LOGITS
     been
    2.02
    been
    1.49
     got
    1.47
     Been
    1.35
    Been
    1.32
     gotta
    1.31
     BEEN
    1.30
     gotten
    1.26
     become
    1.04
     ollut
    1.03
    Activations Density 0.191%

    No Known Activations