© 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. 14-GEMMASCOPE-RES-16K
    11. 8655
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to handling placeholders and variables within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.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
    mybatisplus
    -0.65
     Infórmanos
    -0.58
     increí
    -0.54
     tartalomajánló
    -0.52
     contextLoads
    -0.51
     estekak
    -0.50
    niſſe
    -0.50
     وتسجيلات
    -0.50
    RegressionTest
    -0.50
     незавершена
    -0.49
    POSITIVE LOGITS
    rawDesc
    0.42
    rsiniz
    0.39
     refers
    0.37
     spotted
    0.36
     spots
    0.35
     substitution
    0.35
     refer
    0.35
     spotting
    0.34
     letters
    0.33
     including
    0.33
    Activations Density 0.482%

    No Known Activations