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. 6986
    Prev
    Next
    INDEX
    Explanations

    references to "single" or "child" in various contexts, likely focusing on single-item or single-child entities

    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
    er
    -0.64
     Lehman
    -0.58
     Saj
    -0.54
     Bue
    -0.54
     Zola
    -0.52
    haben
    -0.52
    ené
    -0.52
     Caz
    -0.51
    GOTREF
    -0.51
    Autoritní
    -0.51
    POSITIVE LOGITS
     Child
    1.00
    Child
    0.97
    abetes
    0.80
    Self
    0.76
     Children
    0.76
     Self
    0.72
    Children
    0.71
    Male
    0.70
     Male
    0.69
     Side
    0.69
    Activations Density 0.264%

    No Known Activations