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. 41-GEMMASCOPE-RES-16K
    6. 10555
    Prev
    Next
    INDEX
    Explanations

    practical solutions and methods for tasks or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -2.69
     ourselves
    -2.67
     our
    -2.53
    我們
    -2.19
    We
    -2.17
     We
    -2.13
    我们
    -2.09
    Our
    -2.08
    我们的
    -2.03
     ours
    -2.02
    POSITIVE LOGITS
    StoreMessageInfo
    0.45
    szönöm
    0.44
    AndroidJUnit
    0.41
    Parcelize
    0.40
    umesc
    0.39
    fjspx
    0.37
    NewGuid
    0.37
    ihnachten
    0.36
    webElementXpaths
    0.35
    UnknownFieldSet
    0.34
    Activations Density 0.906%

    No Known Activations