Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12940
    Prev
    Next
    INDEX
    Explanations

    discussions related to societal injustices and privilege dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.53
    Personendaten
    -0.51
     ſon
    -0.49
    HOY
    -0.48
     ſche
    -0.48
     Oval
    -0.48
    Orbital
    -0.47
     ſal
    -0.47
     ſte
    -0.46
     Curiosity
    -0.46
    POSITIVE LOGITS
     ancak
    0.37
     nhưng
    0.36
    ftagPool
    0.35
     palsu
    0.34
     supuestamente
    0.34
     smtplib
    0.34
     perfectamente
    0.34
     but
    0.34
    Архівовано
    0.34
    abbaye
    0.33
    Activations Density 1.377%

    No Known Activations