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. 0-GEMMASCOPE-RES-16K
    6. 7812
    Prev
    Next
    INDEX
    Explanations

    expressions related to instruction or guidance on using software or tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dezelve
    -0.50
    wußt
    -0.49
     zelve
    -0.46
    ientras
    -0.44
    liesslich
    -0.44
     flesta
    -0.43
    новниш
    -0.43
    mutlich
    -0.43
    guien
    -0.42
    ğimiz
    -0.42
    POSITIVE LOGITS
    ть
    0.68
     вести
    0.66
    ίνει
    0.65
    вать
    0.64
     зробити
    0.63
    ContentAsync
    0.62
     mít
    0.61
     робити
    0.59
     провести
    0.58
    θεί
    0.58
    Activations Density 1.500%

    No Known Activations