© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6157
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal opinions or frustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.71
    indd
    -0.59
     maisha
    -0.57
     pleaſure
    -0.56
     perfons
    -0.56
     houſe
    -0.55
    styleable
    -0.52
     uſe
    -0.51
     ſtate
    -0.50
     ufficio
    -0.50
    POSITIVE LOGITS
     rant
    1.36
     rambling
    1.25
     ranting
    1.21
     digress
    1.00
     talk
    0.99
    Rant
    0.97
     Rant
    0.96
     ramb
    0.96
     lecture
    0.86
     sermon
    0.84
    Activations Density 0.282%

    No Known Activations