© 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. 27-GEMMASCOPE-RES-16K
    11. 10013
    Prev
    Next
    INDEX
    Explanations

    moments of realization and reflection in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impres
    -0.40
    ագրություններ
    -0.38
    imp
    -0.38
    $_['
    -0.34
    驚く
    -0.34
     prima
    -0.33
    TemporalType
    -0.33
    probably
    -0.33
    interess
    -0.33
     amaz
    -0.33
    POSITIVE LOGITS
     properly
    0.59
     dessutom
    0.56
     правильно
    0.56
     AssemblyTitle
    0.53
     correctement
    0.52
    properly
    0.52
     consistently
    0.49
    Correct
    0.49
    SharedDtor
    0.48
     ktorí
    0.47
    Activations Density 0.698%

    No Known Activations