© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    expressions of subjective experiences and positive sentiments

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

    Positive sentiment after a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    positive adjectives after was/is

    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
    ISupport
    -0.56
    RenderAtEndOf
    -0.56
     թվական
    -0.52
    lexikon
    -0.49
    amd
    -0.48
    <bos>
    -0.48
    AutoresizingMask
    -0.47
    andu
    -0.47
    vdots
    -0.46
    styleable
    -0.45
    POSITIVE LOGITS
     amazing
    0.88
     fantastic
    0.87
     great
    0.86
     brilliant
    0.85
     wonderful
    0.81
    fantastic
    0.81
     awesome
    0.81
    wonderful
    0.78
     marvelous
    0.77
    great
    0.77
    Activations Density 0.186%

    No Known Activations