Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9565
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and numerical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    batore
    -0.41
     bieber
    -0.41
    zzlies
    -0.39
    ctar
    -0.39
     avocat
    -0.39
    pekte
    -0.39
    ewoo
    -0.38
     himo
    -0.37
    Må
    -0.37
    ragalactic
    -0.37
    POSITIVE LOGITS
     neighbours
    0.65
     forward
    0.60
     neighbour
    0.57
     neighbouring
    0.55
     benach
    0.54
    neighbours
    0.54
    Neighbour
    0.52
     neighbors
    0.50
     rück
    0.49
     backward
    0.49
    Activations Density 1.169%

    No Known Activations