© 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. 16-GEMMASCOPE-RES-16K
    11. 8711
    Prev
    Next
    INDEX
    Explanations

    negative phrases and expressions related to lack of knowledge or evidence

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

    Follows negations (not, no) or absence

    np_acts-logits-general · gemini-2.0-flash

    not any

    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
     purpoſe
    -0.74
     Wayback
    -0.66
     myſelf
    -0.65
     Majefty
    -0.65
     ſeveral
    -0.64
    ſelves
    -0.61
     faſt
    -0.61
    almost
    -0.60
     ſmall
    -0.60
     Reſ
    -0.59
    POSITIVE LOGITS
     any
    0.95
     alcun
    0.74
     CreateTagHelper
    0.72
     quaisquer
    0.67
     alcuna
    0.65
     Any
    0.64
     någon
    0.63
     qualquer
    0.63
     either
    0.63
    либо
    0.62
    Activations Density 0.594%

    No Known Activations