© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8897
    Prev
    Next
    INDEX
    Explanations

    references to race and racial dynamics, particularly concerning Black individuals and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.57
    Personendaten
    -0.49
     שוליים
    -0.49
    +#+#
    -0.43
    RegressionTest
    -0.42
     CreateTagHelper
    -0.42
    dozen
    -0.38
     doute
    -0.38
     doubt
    -0.38
     lenker
    -0.38
    POSITIVE LOGITS
    providedIn
    0.46
     صوتيه
    0.43
    homonymie
    0.42
    AddTagHelper
    0.41
     iParam
    0.41
    optionalTypeArgs
    0.39
     tiguan
    0.37
    CodeAttribute
    0.36
    assertj
    0.36
    tagHelperRunner
    0.35
    Activations Density 0.301%

    No Known Activations