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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7405
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific entities related to scientific reagents and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ồm
    -0.57
     CreateTagHelper
    -0.57
    ')):
    -0.57
    JvmStatic
    -0.57
    VisualStudio
    -0.56
     Audiodateien
    -0.55
    MENAFN
    -0.54
    involved
    -0.53
     Vergrößern
    -0.52
    ReferenceEquals
    -0.52
    POSITIVE LOGITS
    air
    0.93
     Airs
    0.82
    ai
    0.81
     air
    0.79
    AIR
    0.77
     airs
    0.76
     AIR
    0.72
    Air
    0.69
    airs
    0.69
    AI
    0.64
    Activations Density 2.604%

    No Known Activations