© 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. 21-GEMMASCOPE-RES-16K
    11. 14973
    Prev
    Next
    INDEX
    Explanations

    strings that denote error messages and log outputs related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gruß
    -0.59
     van
    -0.58
     or
    -0.56
     del
    -0.55
     di
    -0.54
     es
    -0.54
     da
    -0.51
     say
    -0.51
     par
    -0.51
     int
    -0.51
    POSITIVE LOGITS
     ſhe
    0.98
     pleaſure
    0.97
     purpoſe
    0.95
     Monfieur
    0.94
    The
    0.94
     itſelf
    0.94
     Jefus
    0.92
     myſelf
    0.92
     ſte
    0.92
     ſta
    0.92
    Activations Density 0.159%

    No Known Activations