Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14118
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to software installation and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.40
     myſelf
    -1.27
     itſelf
    -1.25
     Roskov
    -1.21
     Efq
    -1.20
     raiſ
    -1.18
     pleaſure
    -1.17
     poffible
    -1.16
     themſelves
    -1.15
     nahilalakip
    -1.14
    POSITIVE LOGITS
     i
    0.75
     på
    0.72
     med
    0.67
     som
    0.66
     til
    0.60
     om
    0.59
     en
    0.59
     og
    0.58
     kan
    0.57
     till
    0.57
    Activations Density 0.073%

    No Known Activations