© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3805
    Prev
    Next
    INDEX
    Explanations

    expressions related to context and conditions

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

    "In" followed by indefinite/definite article or possessive pronoun

    np_acts-logits-general · gemini-2.0-flash

    in followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.79
     useRouter
    -0.76
    Portale
    -0.76
    Revenir
    -0.74
    Berikut
    -0.72
     useParams
    -0.70
    zzleHttp
    -0.70
    Vidite
    -0.68
    المناصب
    -0.66
    Confira
    -0.66
    POSITIVE LOGITS
     I
    0.76
     my
    0.67
     Honestly
    0.56
    my
    0.55
    I
    0.54
    BTW
    0.53
    aro
    0.51
    so
    0.50
    Honestly
    0.50
    ak
    0.49
    Activations Density 0.181%

    No Known Activations