© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3312
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to screws and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.72
    jgl
    -0.59
     softshell
    -0.57
    Filmographie
    -0.56
    enerbah
    -0.54
    RemoteException
    -0.54
     сме
    -0.53
     midline
    -0.52
    alamus
    -0.52
     JLabel
    -0.52
    POSITIVE LOGITS
    模様
    0.56
    出版年
    0.54
     puntu
    0.51
    越多
    0.49
    getPassword
    0.49
     struttura
    0.49
    WriteBarrier
    0.49
     conferir
    0.49
     structure
    0.48
    Hentet
    0.48
    Activations Density 0.906%

    No Known Activations