© 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. 8-GEMMASCOPE-RES-16K
    6. 10343
    Prev
    Next
    INDEX
    Explanations

    structurally complex elements within the text, such as sections or marked references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.85
    SequentialGroup
    -0.77
    ValueStyle
    -0.73
    RegressionTest
    -0.70
    RegistryLite
    -0.69
     typelib
    -0.66
     CreateTagHelper
    -0.64
     protoimpl
    -0.64
    ьа
    -0.64
    ANTLR
    -0.62
    POSITIVE LOGITS
    thood
    0.61
    hasOwnProperty
    0.58
    ğraf
    0.57
     Scripps
    0.57
    onAttach
    0.56
     triglycerides
    0.55
     greateſt
    0.55
     stb
    0.55
    onesi
    0.55
     Phry
    0.53
    Activations Density 0.235%

    No Known Activations