© 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. 10633
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and individual circumstances

    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
     AssemblyTitle
    -1.00
    存于互联网档案馆
    -0.94
    AddTagHelper
    -0.80
     cherchés
    -0.79
    rxjs
    -0.78
    EDEFAULT
    -0.76
    SourceChecksum
    -0.76
    principalTable
    -0.75
    tagHelperRunner
    -0.75
     AspNetCore
    -0.75
    POSITIVE LOGITS
     yourself
    1.77
     your
    1.40
    yourself
    1.29
    your
    1.25
     Yourself
    1.19
     YOURSELF
    1.16
    Your
    1.14
     Your
    1.13
    Yourself
    1.08
     yourselves
    1.05
    Activations Density 1.235%

    No Known Activations