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. 21-GEMMASCOPE-RES-16K
    6. 7391
    Prev
    Next
    INDEX
    Explanations

    technical comments related to code implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.93
    +#+#
    -0.85
    bootstrapcdn
    -0.84
    ########.
    -0.83
    MLLoader
    -0.82
     transfieras
    -0.82
    writeFieldEnd
    -0.76
     AssemblyVersion
    -0.75
     nahilalakip
    -0.71
     referenties
    -0.70
    POSITIVE LOGITS
    ButtonPressed
    0.47
     specifically
    0.45
     című
    0.45
    AutoresizingMask
    0.42
    pelo
    0.42
     daarom
    0.42
    pec
    0.41
    因此
    0.41
    zerű
    0.41
    getBoolean
    0.41
    Activations Density 0.070%

    No Known Activations