© 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. 25-GEMMASCOPE-RES-16K
    11. 4137
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that imply contrasts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Either
    -0.91
     Either
    -0.88
     invece
    -0.85
    UnusedPrivate
    -0.81
    更是
    -0.79
    either
    -0.78
     malah
    -0.78
     either
    -0.78
     inoltre
    -0.78
     dessutom
    -0.77
    POSITIVE LOGITS
     technically
    1.44
     nominally
    1.28
     initially
    1.23
     admittedly
    1.19
     ostensibly
    1.14
     outwardly
    1.10
     téc
    1.05
     superfic
    1.04
     theoretically
    1.04
     undoubtedly
    0.96
    Activations Density 0.600%

    No Known Activations