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. 9110
    Prev
    Next
    INDEX
    Explanations

    various forms of communication, particularly related to family and relational connections

    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
    Alongside
    -0.82
    Portály
    -0.78
     Alongside
    -0.76
    tldr
    -0.73
    klart
    -0.72
     weirdly
    -0.71
     Notably
    -0.71
     propOrder
    -0.71
    ⁠
    -0.70
     prioriti
    -0.70
    POSITIVE LOGITS
     skall
    0.97
     muß
    0.95
     läßt
    0.83
     thru
    0.80
     daß
    0.74
     IMHO
    0.73
     Вам
    0.69
     Schluß
    0.69
     definately
    0.67
    luß
    0.66
    Activations Density 0.664%

    No Known Activations