© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12384
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to software, programming, or systems operations

    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
     Efq
    -2.31
     Monfieur
    -2.17
     myſelf
    -2.09
     Anſ
    -2.08
     ―――――
    -2.08
     Houſe
    -2.06
     Jefus
    -2.04
     Majefty
    -2.04
     pleaſure
    -2.04
     iſt
    -2.04
    POSITIVE LOGITS
     
    0.94
     de
    0.87
     à
    0.79
     d
    0.78
    <eos>
    0.78
     des
    0.77
     la
    0.77
     en
    0.76
     le
    0.76
     L
    0.74
    Activations Density 1.640%

    No Known Activations