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. 12-GEMMASCOPE-RES-16K
    6. 469
    Prev
    Next
    INDEX
    Explanations

    terms related to selenium and its compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mener
    -0.72
    oporosis
    -0.72
     Obrador
    -0.69
     Worthington
    -0.68
    rdoba
    -0.68
     Crot
    -0.68
     Langer
    -0.66
    Couch
    -0.66
    ########.
    -0.63
    ĵo
    -0.63
    POSITIVE LOGITS
    Se
    1.32
     Se
    1.26
     SE
    1.20
     Seitz
    1.14
     Selig
    1.14
     Segal
    1.11
     Seidel
    1.10
    SE
    1.08
     Sewell
    1.07
     Seif
    1.05
    Activations Density 0.201%

    No Known Activations