© 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. 12-GEMMASCOPE-RES-16K
    6. 4939
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orton
    -0.41
     Terrell
    -0.39
                      
    -0.39
    Monroe
    -0.38
     acontecer
    -0.37
     horrific
    -0.37
    abbaye
    -0.37
    hringer
    -0.36
     ferocious
    -0.36
                     
    -0.36
    POSITIVE LOGITS
     Advice
    1.69
     advice
    1.69
    Advice
    1.63
    advice
    1.60
     advise
    1.55
     ADVICE
    1.52
     advising
    1.41
     advised
    1.37
     advises
    1.37
     ADVIS
    1.36
    Activations Density 0.113%

    No Known Activations