© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12831
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ik" and its variations, often associated with specific contexts or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     couro
    -0.40
     cuero
    -0.39
    Redaktion
    -0.38
     cartões
    -0.38
     bañera
    -0.37
    rijfs
    -0.37
     spreken
    -0.37
     pekan
    -0.36
    fromnode
    -0.36
    anglicky
    -0.36
    POSITIVE LOGITS
    ik
    1.38
    IK
    1.13
    iki
    0.77
    ikas
    0.76
     IK
    0.74
    İK
    0.71
    iku
    0.68
    lik
    0.68
    ikin
    0.68
    tik
    0.67
    Activations Density 0.466%

    No Known Activations