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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10361
    Prev
    Next
    INDEX
    Explanations

    concepts related to media and discourse in sociological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.31
     itſelf
    -1.30
     raiſ
    -1.22
     ſta
    -1.22
     Efq
    -1.17
     Jefus
    -1.16
     purpoſe
    -1.11
     himſelf
    -1.09
     ſever
    -1.08
     iſt
    -1.07
    POSITIVE LOGITS
     sub
    0.52
     di
    0.49
     in
    0.47
    ,
    0.47
     духовке
    0.46
     que
    0.46
     Per
    0.45
     para
    0.45
    ;
    0.45
     entro
    0.43
    Activations Density 0.559%

    No Known Activations