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. 14714
    Prev
    Next
    INDEX
    Explanations

    references to specific cell lines and culture conditions

    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
    URLException
    -0.78
     viewWillAppear
    -0.60
    endforeach
    -0.57
    onViewCreated
    -0.57
    Referencie
    -0.56
    VersionUID
    -0.56
    __(/*!
    -0.55
    WebMethod
    -0.54
    ULUS
    -0.53
    ViewInit
    -0.53
    POSITIVE LOGITS
     Meksiku
    0.57
    MessageTagHelper
    0.53
    scriptcase
    0.51
    IntoConstraints
    0.50
    WithIOException
    0.47
     entrada
    0.46
     дописавши
    0.46
    "):
    0.46
    Tikang
    0.45
    [];
    
    0.44
    Activations Density 0.678%

    No Known Activations