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. 12-GEMMASCOPE-RES-16K
    6. 6230
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to health and medicinal properties of natural substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RIPRODUZIONE
    -0.96
     pleaſure
    -0.90
    AccessorTable
    -0.83
    yntaxException
    -0.82
     Efq
    -0.82
    WriteTagHelper
    -0.82
     שוליים
    -0.82
     noqa
    -0.82
     purpoſe
    -0.82
    omitempty
    -0.82
    POSITIVE LOGITS
    Mis
    0.47
     research
    0.44
     Mis
    0.42
    mis
    0.42
     le
    0.42
     use
    0.41
     claims
    0.41
     health
    0.41
     DIY
    0.41
     misuse
    0.40
    Activations Density 0.492%

    No Known Activations