© 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. 14-GEMMASCOPE-RES-16K
    11. 7435
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions and conjunctions indicating relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.59
    AndroidJUnit
    -0.53
    ]--;
    -0.50
    SpringBootTest
    -0.49
    >`;
    -0.49
    msgSender
    -0.49
     GeoNames
    -0.47
    skjaer
    -0.47
    맞
    -0.47
     GenerationType
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.77
    CodeAttribute
    0.68
    broek
    0.64
     BoxDecoration
    0.63
    IsContent
    0.56
    CLUDING
    0.55
     humaine
    0.55
     irmão
    0.55
     editados
    0.53
     quelconque
    0.53
    Activations Density 1.311%

    No Known Activations