© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13974
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and descriptions of oneself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Izvori
    -0.41
     ease
    -0.40
     Ease
    -0.38
     AssertionError
    -0.36
     Wirksamkeit
    -0.35
    Ease
    -0.35
     repeatedly
    -0.35
     allegedly
    -0.35
     Grossman
    -0.35
    明らかに
    -0.34
    POSITIVE LOGITS
    ImageContext
    0.60
     AssemblyTitle
    0.59
    AddTagHelper
    0.59
    webElementXpaths
    0.59
    Personensuche
    0.57
    httphttps
    0.56
    contentLoaded
    0.53
    queryInterface
    0.53
    WithIOException
    0.52
     MainAxisSize
    0.50
    Activations Density 0.299%

    No Known Activations