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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8774
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 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
    .
    -0.65
     BIG
    -0.55
    tanleria
    -0.53
    ira
    -0.53
    big
    -0.51
     big
    -0.50
    ;
    -0.50
    ,
    -0.49
     Big
    -0.49
    >
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.99
    protoimpl
    0.97
     AssemblyCulture
    0.91
     Normdatei
    0.89
     myſelf
    0.85
     reaſon
    0.85
     purpoſe
    0.85
     snippetHide
    0.79
     pleaſure
    0.79
     ſtate
    0.78
    Activations Density 0.029%

    No Known Activations