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. 2828
    Prev
    Next
    INDEX
    Explanations

    terms related to growth and development

    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
    __*/
    -0.59
    Composable
    -0.57
    }}],
    -0.54
    //};
    -0.54
    lorum
    -0.54
     lära
    -0.52
     practising
    -0.51
    DllImport
    -0.51
    albero
    -0.51
     totalité
    -0.51
    POSITIVE LOGITS
     spurt
    0.86
     rate
    0.84
     rates
    0.73
     trajectory
    0.72
     Rate
    0.68
    addCriterion
    0.66
     spur
    0.66
     acceleration
    0.65
     trajectories
    0.65
     Acceleration
    0.64
    Activations Density 0.147%

    No Known Activations