Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11316
    Prev
    Next
    INDEX
    Explanations

    negations and the term "no" in various contexts

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

    Sentences expressing doubt or negation with "no"

    np_acts-logits-general · gemini-2.0-flash

    no followed by doubt/question/need

    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
    ValueStyle
    -0.59
     mosso
    -0.56
     Roskov
    -0.55
     remarquer
    -0.52
     constater
    -0.51
     ISTAT
    -0.51
    riwal
    -0.49
    ばかり
    -0.49
     dõi
    -0.45
    coglie
    -0.45
    POSITIVE LOGITS
     better
    0.81
     denying
    0.72
     doubt
    0.69
    GraphicsUnit
    0.68
     excuse
    0.68
    excuse
    0.66
    escaping
    0.66
     escaping
    0.65
     guarantee
    0.65
     point
    0.64
    Activations Density 0.129%

    No Known Activations