© 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. 4-GEMMASCOPE-RES-16K
    11. 2771
    Prev
    Next
    INDEX
    Explanations

    various types and categories of networks and classifications within specified subgroups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.71
     RequestMethod
    -0.58
    퓨
    -0.56
    %%
    -0.56
    mapsto
    -0.55
    ++.
    -0.53
     Schoen
    -0.52
     campaign
    -0.49
     Rosen
    -0.49
    werth
    -0.49
    POSITIVE LOGITS
     sub
    1.13
     subsection
    1.01
     subsections
    0.98
     Sub
    0.93
     subs
    0.89
     subsystems
    0.89
     SUB
    0.88
    SUB
    0.88
    Sub
    0.87
     getSub
    0.86
    Activations Density 0.146%

    No Known Activations