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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2830
    Prev
    Next
    INDEX
    Explanations

    instances of the word "kind" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cifix
    -1.12
     Roach
    -1.03
    ceuticals
    -0.87
    Дереккөздер
    -0.86
     Geller
    -0.85
    ectomy
    -0.85
     Matos
    -0.81
     Rossa
    -0.81
     verru
    -0.81
    bleven
    -0.80
    POSITIVE LOGITS
     Kind
    1.56
     KIND
    1.53
    kind
    1.50
    Kind
    1.45
     kind
    1.43
    KIND
    1.38
    Kinds
    1.27
    kinds
    1.26
     Kinds
    1.17
     kinds
    1.13
    Activations Density 0.044%

    No Known Activations