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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6660
    Prev
    Next
    INDEX
    Explanations

    negative assessments or critiques of experiences and quality

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

    Negation of positive qualities or recommendations

    np_acts-logits-general · gemini-2.0-flash

    negated descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.76
     continúas
    -0.61
     simply
    -0.59
     propOrder
    -0.58
    simply
    -0.57
    TintMode
    -0.57
    CppMethod
    -0.57
    次第
    -0.56
    ่านั้น
    -0.56
     pleaſure
    -0.52
    POSITIVE LOGITS
     bad
    0.68
     flashy
    0.56
    bad
    0.55
     overly
    0.55
    NameInMap
    0.54
     كومونز
    0.54
    extensive
    0.53
     zbyt
    0.52
    Extensive
    0.52
     shabby
    0.49
    Activations Density 0.122%

    No Known Activations