© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 597
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtate
    -1.08
     auffi
    -1.06
     purpoſe
    -1.02
     houſe
    -0.99
     pleaſure
    -0.96
     Monfieur
    -0.95
     ſever
    -0.95
     cauſe
    -0.94
     ſeveral
    -0.94
     Chriftian
    -0.93
    POSITIVE LOGITS
     was
    1.83
     were
    1.50
     WAS
    1.46
     Was
    1.43
     is
    1.41
     WERE
    1.27
    Was
    1.23
     Were
    1.21
    was
    1.21
     be
    1.17
    Activations Density 0.450%

    No Known Activations