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. 23-GEMMASCOPE-RES-16K
    6. 9161
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to claims and complaints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arkivert
    -0.58
    それとも
    -0.54
    setdefault
    -0.49
    |()
    -0.48
    BagLayout
    -0.46
    řevě
    -0.46
     Autre
    -0.45
    ustimmung
    -0.43
    воря
    -0.43
    ^(@)
    -0.43
    POSITIVE LOGITS
     therefore
    4.38
    therefore
    3.63
     thus
    3.59
     hence
    3.52
     Therefore
    3.42
    Therefore
    3.34
    hence
    2.95
     consequently
    2.92
     donc
    2.89
     Hence
    2.87
    Activations Density 1.634%

    No Known Activations