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. 0-GEMMASCOPE-RES-16K
    6. 166
    Prev
    Next
    INDEX
    Explanations

    instances of the word "achieve."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.74
    __':
    -0.69
     disambiguazione
    -0.69
     متعلقه
    -0.67
    saraba
    -0.67
    Erreferentziak
    -0.67
    sizeCache
    -0.65
     старости
    -0.65
     Drapeau
    -0.65
     дописавши
    -0.65
    POSITIVE LOGITS
     achieve
    2.71
     achieved
    2.52
     achieves
    2.44
     achieving
    2.35
     accomplish
    2.31
    achieve
    2.29
     Achieve
    2.26
    Achie
    2.24
    achieved
    2.02
     Achieving
    1.99
    Activations Density 0.140%

    No Known Activations