© 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. 16314
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their actions

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

    Followed by past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by a verb

    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
    Said
    -0.96
     say
    -0.94
    Says
    -0.88
     sayin
    -0.88
     dikatakan
    -0.88
    say
    -0.87
     says
    -0.86
     Said
    -0.85
     said
    -0.84
     SAID
    -0.82
    POSITIVE LOGITS
     pihaknya
    0.70
     liever
    0.65
     regretted
    0.65
     regrets
    0.65
    ImageContext
    0.62
     sentía
    0.60
     expects
    0.57
     hoped
    0.56
     “
    0.56
     learned
    0.56
    Activations Density 0.253%

    No Known Activations