© 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. 22-GEMMASCOPE-RES-16K
    11. 13264
    Prev
    Next
    INDEX
    Explanations

    indicative verbs related to existence and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a passive verb

    np_acts-logits-general · gemini-2.0-flash

    passive verbs after forms of to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chtete
    -0.56
    kazu
    -0.50
    calling
    -0.49
    baik
    -0.49
     ích
    -0.48
    setVerticalGroup
    -0.48
     löyty
    -0.47
     reconhecimento
    -0.47
     arrivo
    -0.47
    hoeddwyd
    -0.46
    POSITIVE LOGITS
     told
    1.63
     asked
    1.55
     given
    1.46
     instructed
    1.39
     encouraged
    1.24
     advised
    1.23
     allowed
    1.20
     offered
    1.20
     invited
    1.17
     Told
    1.17
    Activations Density 0.555%

    No Known Activations