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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8107
    Prev
    Next
    INDEX
    Explanations

    instances of the word "written" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.35
     Савезне
    -1.33
    expandindo
    -1.26
     AssemblyCompany
    -1.25
    GEBURTSDATUM
    -1.21
     الحره
    -1.20
     ModelExpression
    -1.16
    SourceChecksum
    -1.15
    انيف
    -1.10
     CreateTagHelper
    -1.10
    POSITIVE LOGITS
     written
    0.88
     an
    0.63
     
    0.60
     for
    0.58
    ​
    0.56
     with
    0.56
     followed
    0.55
     in
    0.54
     a
    0.54
     as
    0.51
    Activations Density 0.128%

    No Known Activations