© 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-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4633
    Prev
    Next
    INDEX
    Explanations

    conversational expressions and phrases that convey personal hopes and solutions

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

    text that sounds like informal, conversational online communication (with spelling errors, slang, and personal storytelling).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @carolinacamassa
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.46
     você
    -0.38
     noël
    -0.36
     không
    -0.35
     you
    -0.35
     — 
    -0.35
     می‌توانید
    -0.35
     usted
    -0.35
    říklad
    -0.34
    IsNotEmpty
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.92
     ur
    0.90
     abt
    0.85
     u
    0.82
     ppl
    0.81
     frm
    0.79
     dat
    0.79
     lyk
    0.77
     cud
    0.74
     tht
    0.74
    Activations Density 0.257%

    No Known Activations