© 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. 23-GEMMASCOPE-RES-16K
    11. 4525
    Prev
    Next
    INDEX
    Explanations

    terms related to biological systems and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.70
    ⓧ
    -0.68
     illegal
    -0.65
     okay
    -0.64
     horrible
    -0.64
     متعلقه
    -0.64
     invented
    -0.63
     awful
    -0.62
     stupid
    -0.61
     terrible
    -0.61
    POSITIVE LOGITS
     Roskov
    0.65
     increasingly
    0.61
     altrimenti
    0.58
     pertanto
    0.55
    increasing
    0.55
     voici
    0.52
     élo
    0.51
     varandra
    0.50
    Vanjske
    0.49
    Insee
    0.47
    Activations Density 0.617%

    No Known Activations