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. 25-GEMMASCOPE-RES-16K
    6. 5773
    Prev
    Next
    INDEX
    Explanations

    expressions related to requests for assistance or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.58
    AddTagHelper
    -0.55
    Tikang
    -0.54
    InputBorder
    -0.54
     BnF
    -0.53
    Попис
    -0.51
    PasswordEncoder
    -0.51
    يكب
    -0.51
     tayang
    -0.51
    writeFieldEnd
    -0.50
    POSITIVE LOGITS
     me
    4.02
    me
    1.81
     мне
    1.74
     меня
    1.74
     mnie
    1.73
     conmigo
    1.67
     мной
    1.61
     comigo
    1.59
     मुझे
    1.49
     tôi
    1.43
    Activations Density 0.762%

    No Known Activations