© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7723
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to thread management and synchronization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Telerik
    -0.38
    انجليز
    -0.35
    djangoproject
    -0.35
    VertexAttrib
    -0.34
     abstracta
    -0.33
     aparelho
    -0.33
    olstadt
    -0.33
    模糊
    -0.32
     marbre
    -0.32
    Leben
    -0.31
    POSITIVE LOGITS
     lock
    1.53
     locks
    1.44
    lock
    1.38
     Lock
    1.35
    Lock
    1.35
     locking
    1.34
     Locks
    1.26
     mutex
    1.25
     LOCK
    1.24
    locks
    1.23
    Activations Density 0.594%

    No Known Activations