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. 5-GEMMASCOPE-RES-16K
    6. 12695
    Prev
    Next
    INDEX
    Explanations

    phrases related to the duration and frequency of actions or experiences

    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
    Personendaten
    -1.10
    //
    -0.86
     CreateTagHelper
    -0.82
    IndentedString
    -0.82
     Efq
    -0.81
    ThroughAttribute
    -0.77
     greateſt
    -0.74
    TypedDataSet
    -0.72
     againſt
    -0.71
     GoogleFonts
    -0.71
    POSITIVE LOGITS
     until
    0.45
    ch
    0.44
    rez
    0.44
    .
    0.44
    velocityX
    0.43
     after
    0.43
    órica
    0.43
    r
    0.43
     litté
    0.42
    in
    0.42
    Activations Density 0.285%

    No Known Activations