© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9140
    Prev
    Next
    INDEX
    Explanations

    phrases related to volunteer services and support in healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
     comms
    -0.86
     weirdly
    -0.84
     shitty
    -0.83
     freaking
    -0.83
     bestie
    -0.81
     badass
    -0.80
     hipster
    -0.79
    iſchen
    -0.77
     dodgy
    -0.77
     autorytatywna
    -0.77
    POSITIVE LOGITS
     skall
    0.63
     muß
    0.51
     quelquefois
    0.48
     läßt
    0.46
    faßt
    0.42
     individus
    0.42
     doskona
    0.40
     løpet
    0.37
    incontro
    0.37
     genieten
    0.37
    Activations Density 0.681%

    No Known Activations