© 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. 706
    Prev
    Next
    INDEX
    Explanations

    mentions of budget management and financial discussions

    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
     Whilst
    -1.60
    Whilst
    -1.54
     whilst
    -1.33
     poichè
    -1.11
     FUCKING
    -1.08
     fucking
    -1.06
    Fuck
    -1.02
     Amongst
    -1.01
     twenty
    -0.99
     läßt
    -0.98
    POSITIVE LOGITS
     —
    1.01
     
    0.97
     
    0.91
     ``
    0.90
    ``
    0.86
    ȁ
    0.82
     Sept
    0.82
     ¦
    0.81
    ,’’
    0.81
     ‘‘
    0.78
    Activations Density 1.703%

    No Known Activations