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. 7001
    Prev
    Next
    INDEX
    Explanations

    structured data or markup elements

    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
    etheless
    -0.96
    NUMX
    -0.87
     itſelf
    -0.85
     Monfieur
    -0.79
     myſelf
    -0.79
    +:+
    -0.75
    )";
    
    -0.74
    kyou
    -0.74
     CWE
    -0.72
    Incluso
    -0.70
    POSITIVE LOGITS
    .—
    0.62
    ,—
    0.50
    —
    0.50
    .
    0.49
    InputTagHelper
    0.47
     ditto
    0.46
    theilung
    0.45
    ._
    0.45
    ,
    0.45
     fios
    0.44
    Activations Density 0.414%

    No Known Activations