© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6113
    Prev
    Next
    INDEX
    Explanations

    concepts related to roles, responsibilities, and spiritual or religious duties within a community context

    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
     vectorielles
    -0.97
    脚注の使い方
    -0.69
     présentes
    -0.68
     känna
    -0.68
     transitioning
    -0.67
     supérieures
    -0.65
     kasarigan
    -0.65
     similaire
    -0.65
     réfrig
    -0.65
    abestanden
    -0.65
    POSITIVE LOGITS
     надо
    0.55
     doubtless
    0.53
     CreateTagHelper
    0.51
     furnish
    0.49
     accords
    0.49
     neceff
    0.49
    DOCTYPE
    0.48
     muß
    0.48
    ûte
    0.48
    Надо
    0.47
    Activations Density 0.697%

    No Known Activations