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. 14224
    Prev
    Next
    INDEX
    Explanations

    UI components in Android layout files

    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
    interopRequire
    -0.76
    corrhi
    -0.66
    Liang
    -0.66
     Liang
    -0.66
    أل
    -0.64
     NACIONAL
    -0.63
    ceto
    -0.63
     consegna
    -0.61
    Naissance
    -0.61
    posedge
    -0.61
    POSITIVE LOGITS
    TextView
    2.84
     TextView
    2.20
     textView
    1.18
    ImageView
    1.16
    textView
    1.07
     ImageView
    1.05
    textview
    0.87
    aarrggbb
    0.77
     UILabel
    0.72
    UILabel
    0.72
    Activations Density 0.039%

    No Known Activations