© 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. 23-GEMMASCOPE-RES-16K
    11. 6722
    Prev
    Next
    INDEX
    Explanations

    references to data structures or algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    patterns related to numerical data and its representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.96
    ंदीखरीदारी
    -0.70
     GenerationType
    -0.67
    localObject
    -0.67
    坞
    -0.66
    ر
    -0.63
    AsUp
    -0.60
    IUrlHelper
    -0.60
     
    -0.60
    stdc
    -0.59
    POSITIVE LOGITS
     myſelf
    1.20
     Jefus
    1.19
     Theſe
    1.17
     himſelf
    1.15
     itſelf
    1.12
     uſed
    1.09
     Anſ
    1.08
     purpoſe
    1.07
     raiſ
    1.06
     themſelves
    1.05
    Activations Density 2.630%

    No Known Activations