© 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. 25-GEMMASCOPE-RES-16K
    11. 2756
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and its variations, indicating a focus on locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    紹介します
    -0.69
    美国
    -0.64
    狙
    -0.61
    考える
    -0.61
     nationaux
    -0.61
     verrez
    -0.60
    抑
    -0.58
    LabelTagHelper
    -0.58
     ModelExpression
    -0.57
    urlopen
    -0.57
    POSITIVE LOGITS
     addition
    1.40
     accordance
    1.31
     conjunction
    1.22
     relation
    1.22
     terms
    1.20
     order
    1.18
     lieu
    1.15
     spite
    1.14
     favor
    0.99
     vitro
    0.98
    Activations Density 1.268%

    No Known Activations