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. 5-GEMMASCOPE-RES-16K
    6. 2220
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and daily 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
    BACKEND
    -0.63
    intéress
    -0.59
    Backend
    -0.57
     ogrodow
    -0.57
    Domen
    -0.56
     Backend
    -0.56
    arrivo
    -0.55
    BACA
    -0.54
     AppComponent
    -0.53
    Portale
    -0.53
    POSITIVE LOGITS
     goes
    0.97
     go
    0.91
    Goes
    0.88
     WENT
    0.85
    Went
    0.84
     Goes
    0.83
     went
    0.82
     Going
    0.82
     goin
    0.81
    OGND
    0.80
    Activations Density 0.116%

    No Known Activations