© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 509
    Prev
    Next
    INDEX
    Explanations

    financial terms and conditions related to payments and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    financial and transaction-related details (like payment methods, dates, and transaction terms).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behaviour
    -0.84
     recognised
    -0.84
     generalised
    -0.82
     behavioural
    -0.81
     neighbouring
    -0.80
     personalised
    -0.77
     tumour
    -0.77
     localised
    -0.77
     endeavours
    -0.77
     organisations
    -0.76
    POSITIVE LOGITS
    favorite
    0.71
    Favorite
    0.70
     favorite
    0.69
     geologic
    0.68
     favorably
    0.67
    Honors
    0.66
     honored
    0.65
     FAVORITE
    0.65
     counselors
    0.65
     counselor
    0.65
    Activations Density 2.256%

    No Known Activations