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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 3960
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles and impediments in various contexts

    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
    󠁿
    -0.52
    []>(
    -0.47
    )}_{
    -0.45
    ۜ
    -0.44
    quake
    -0.44
     AssemblyProduct
    -0.43
    billon
    -0.43
     Leone
    -0.42
    dos
    -0.42
     profundas
    -0.42
    POSITIVE LOGITS
     obstacles
    1.36
     impediments
    1.34
     obstacle
    1.34
     impediment
    1.25
     obstruction
    1.25
     obstructions
    1.22
     obstruct
    1.21
     hindrance
    1.20
     barriers
    1.18
     blocked
    1.17
    Activations Density 0.473%

    No Known Activations