© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10164
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and organizational structures

    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
     juſ
    -0.53
     Boas
    -0.52
     JpaRepository
    -0.51
     houſe
    -0.51
    PerformLayout
    -0.50
    ---*/
    -0.50
     protoimpl
    -0.49
     tranſ
    -0.49
     purpoſe
    -0.48
    MigrationBuilder
    -0.48
    POSITIVE LOGITS
    чи
    0.69
    ч
    0.67
    č
    0.66
    ЧИ
    0.64
    ча
    0.62
    че
    0.61
    чен
    0.61
    ЧЕ
    0.58
    чите
    0.58
    чили
    0.57
    Activations Density 0.172%

    No Known Activations