© 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. 10739
    Prev
    Next
    INDEX
    Explanations

    references related to identity and belonging, particularly in social and economic contexts

    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
    httphttps
    -0.48
    XmlAccessorType
    -0.48
    GenerationType
    -0.42
    buttonShape
    -0.41
     kedua
    -0.40
    AlterField
    -0.39
    遽
    -0.39
     acesta
    -0.38
    writerow
    -0.37
     dayan
    -0.36
    POSITIVE LOGITS
     their
    0.88
     themselves
    0.86
    their
    0.81
     Leurs
    0.76
    themselves
    0.75
    Their
    0.73
    他們的
    0.70
    他们的
    0.70
     ihre
    0.69
     leurs
    0.66
    Activations Density 0.770%

    No Known Activations