© 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. 18-GEMMASCOPE-RES-16K
    6. 8267
    Prev
    Next
    INDEX
    Explanations

    expressions of personal thoughts and experiences

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

    "I," "we," or "it" followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.62
    transQ
    -0.60
     surla
    -0.59
    存于互联网档案馆
    -0.57
    addCriterion
    -0.56
    RegressionTest
    -0.55
    ("")]
    -0.55
    SequentialGroup
    -0.52
    ícone
    -0.52
    ronique
    -0.51
    POSITIVE LOGITS
    eaways
    0.59
     voidaan
    0.57
     worth
    0.56
     Suff
    0.53
     canne
    0.53
     can
    0.52
    won
    0.51
     canto
    0.51
     можно
    0.51
    Browsable
    0.50
    Activations Density 0.291%

    No Known Activations