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. 15-GEMMASCOPE-RES-16K
    6. 12742
    Prev
    Next
    INDEX
    Explanations

    elements related to familial relationships and marital status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    feitura
    -0.58
    +#+
    -0.53
     face
    -0.50
     correctes
    -0.49
    τον
    -0.49
     tanong
    -0.49
     MaterialApp
    -0.48
    生平
    -0.47
    ❉
    -0.46
    )++;
    -0.46
    POSITIVE LOGITS
     existing
    0.87
    existing
    0.83
     Existing
    0.81
    Existing
    0.79
     already
    0.74
     EXISTING
    0.73
     preexisting
    0.72
    已经有
    0.71
    already
    0.71
     previous
    0.71
    Activations Density 0.182%

    No Known Activations