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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14828
    Prev
    Next
    INDEX
    Explanations

    phrases related to explanations or elaborations of concepts

    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
    
    -0.80
     autorytatywna
    -0.78
    IsMutable
    -0.75
    $_['
    -0.74
     TextInputType
    -0.69
     ligiloj
    -0.68
    Personendaten
    -0.63
    /**
    -0.63
     gynhyrchwyd
    -0.63
    expandindo
    -0.62
    POSITIVE LOGITS
     first
    0.39
     Firstly
    0.38
    Firstly
    0.37
    先
    0.37
     firstly
    0.35
    就要
    0.35
     Let
    0.33
    首先
    0.33
     First
    0.32
     Wolken
    0.32
    Activations Density 0.566%

    No Known Activations