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. 7-GEMMASCOPE-RES-16K
    6. 15648
    Prev
    Next
    INDEX
    Explanations

    articles and nouns that suggest the presence of an object or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    więcej
    -0.35
    }}^
    -0.33
    abestanden
    -0.32
    hånd
    -0.31
    ++]=
    -0.29
    PositiveButton
    -0.29
     Wikimedijinoj
    -0.29
     tùy
    -0.29
     powiet
    -0.28
     puțin
    -0.28
    POSITIVE LOGITS
    webElementXpaths
    0.67
     betweenstory
    0.64
     Италијани
    0.63
     ioutil
    0.52
     Photocase
    0.52
    uxxxx
    0.51
     queſto
    0.50
    
    0.50
     purpoſe
    0.49
     snippetHide
    0.49
    Activations Density 0.711%

    No Known Activations