© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8521
    Prev
    Next
    INDEX
    Explanations

    the word "kind" and its variations, indicating a focus on different types or categories of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.98
    AddTagHelper
    -0.97
    Дереккөздер
    -0.94
     Matos
    -0.90
     hostages
    -0.81
    bleven
    -0.81
    ceuticals
    -0.80
     Jagger
    -0.80
    freiheit
    -0.79
    POSITIVE LOGITS
     Kind
    2.17
    kind
    2.14
     kind
    2.11
    Kind
    2.07
     KIND
    2.04
    KIND
    1.92
    kinds
    1.55
     kinds
    1.51
     Kinds
    1.47
    Kinds
    1.46
    Activations Density 0.040%

    No Known Activations