© 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. 3-GEMMASCOPE-RES-16K
    11. 8077
    Prev
    Next
    INDEX
    Explanations

    terms related to existence or presence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.06
     betweenstory
    -1.05
     houſe
    -1.00
     Jefus
    -0.99
     myſelf
    -0.97
     fevere
    -0.92
     pleaſure
    -0.90
     cauſe
    -0.89
     Egli
    -0.88
     Houſe
    -0.87
    POSITIVE LOGITS
     có
    3.15
     Có
    2.19
    Có
    2.10
    có
    2.10
     CÓ
    1.91
    CÓ
    1.40
    มี
    1.00
    有
    0.90
     cso
    0.88
     co
    0.82
    Activations Density 0.039%

    No Known Activations