© 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. 15-GEMMASCOPE-RES-16K
    11. 2665
    Prev
    Next
    INDEX
    Explanations

    terms related to online connectivity and collaboration tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.50
    #+#
    -0.50
    はじめに
    -0.49
    fortawesome
    -0.47
    nál
    -0.45
    спорти
    -0.45
    Autoritní
    -0.44
    })).
    -0.44
    StructEnd
    -0.43
     напи
    -0.42
    POSITIVE LOGITS
     remote
    1.10
     virtual
    1.09
     remotely
    0.99
     remoto
    0.97
    remote
    0.96
     Remote
    0.90
    virtual
    0.89
     Virtual
    0.89
     online
    0.86
    Remote
    0.85
    Activations Density 0.217%

    No Known Activations