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. 2-GEMMASCOPE-RES-16K
    6. 6874
    Prev
    Next
    INDEX
    Explanations

    words related to height

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CascadeType
    -0.62
     provided
    -0.58
     event
    -0.57
    raad
    -0.56
    ****************
    -0.54
    Provided
    -0.54
     dien
    -0.53
    緊
    -0.51
    provided
    -0.50
    ョ
    -0.50
    POSITIVE LOGITS
     tall
    1.14
     taller
    1.11
    Older
    1.10
     Tall
    1.05
    Tall
    1.05
     Older
    1.03
     older
    0.98
    tall
    0.95
     ältere
    0.90
     MainAxisSize
    0.90
    Activations Density 0.064%

    No Known Activations