© 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. 2-GEMMASCOPE-RES-16K
    11. 7042
    Prev
    Next
    INDEX
    Explanations

    programming-related actions and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.63
     Италијани
    -0.63
    ])));
    -0.62
    iecie
    -0.62
    "]').
    -0.60
    _));
    -0.60
    RTLD
    -0.60
     ویکی‌پدی
    -0.60
    }{#
    -0.59
    "]));
    -0.57
    POSITIVE LOGITS
    enumi
    0.74
     Trouver
    0.68
     ולה
    0.65
    Revenir
    0.61
    Faire
    0.58
     Saltar
    0.57
    íteni
    0.57
    ñar
    0.55
    ricular
    0.54
    ificar
    0.54
    Activations Density 0.042%

    No Known Activations