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. 12-GEMMASCOPE-RES-16K
    6. 7447
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "kind" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    -1.15
     Roach
    -1.07
    Дереккөздер
    -1.03
     חיצוניים
    -0.94
    ectomy
    -0.93
    AddTagHelper
    -0.93
     Rossa
    -0.91
    décoration
    -0.91
    operatively
    -0.89
     Matos
    -0.85
    POSITIVE LOGITS
     Kind
    1.41
     KIND
    1.36
    kind
    1.35
     kind
    1.33
    Kind
    1.32
    KIND
    1.25
    Kinds
    1.15
     kinds
    1.09
    kinds
    1.08
     Kinds
    1.04
    Activations Density 0.071%

    No Known Activations