Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12597
    Prev
    Next
    INDEX
    Explanations

    corporate entities and structures within business contexts

    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
    theless
    -0.63
     ddelweddau
    -0.60
     FormBuilder
    -0.55
    たとえば
    -0.55
    tonode
    -0.52
    例えば
    -0.51
    ább
    -0.50
    比如说
    -0.49
    hdashline
    -0.49
    uties
    -0.48
    POSITIVE LOGITS
     which
    1.32
     formerly
    1.15
    formerly
    1.10
    which
    1.05
     aka
    1.03
     whose
    1.01
    whose
    0.94
    aka
    0.90
     Formerly
    0.89
    Formerly
    0.88
    Activations Density 0.529%

    No Known Activations