© 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. 19-GEMMASCOPE-RES-16K
    11. 2728
    Prev
    Next
    INDEX
    Explanations

    sequences of escaped characters and formatting commands in code or technical text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.64
    /
    -0.60
     
    -0.59
     multi
    -0.56
    ,
    -0.55
     gran
    -0.52
     r
    -0.51
     pol
    -0.51
    -
    -0.51
     source
    -0.50
    POSITIVE LOGITS
    Datuak
    1.13
     hObject
    1.03
     itſelf
    1.01
    findpost
    1.00
    Personensuche
    0.98
     useAppContext
    0.97
     houſe
    0.94
     ſche
    0.94
     Monfieur
    0.94
    }")]
    0.93
    Activations Density 0.006%

    No Known Activations