© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13410
    Prev
    Next
    INDEX
    Explanations

    percentages related to financial or caregiving responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROIT
    -0.50
     مشين
    -0.49
    mique
    -0.46
     frühen
    -0.45
    tagHelperRunner
    -0.43
    Positioned
    -0.43
    cheidet
    -0.42
    amboo
    -0.41
    امي
    -0.41
    Nos
    -0.40
    POSITIVE LOGITS
     AssemblyTitle
    0.87
     للاسماء
    0.83
    Personendaten
    0.80
     nakalista
    0.75
    المناصب
    0.75
    bootstrapcdn
    0.71
    AutoField
    0.67
    Portale
    0.63
     DataTypes
    0.60
    ]")]
    0.60
    Activations Density 0.704%

    No Known Activations