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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13570
    Prev
    Next
    INDEX
    Explanations

    terms related to obstacles and barriers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    obstacles or impediments

    np_acts-logits-general · gemini-2.0-flash

    obstacles and barriers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuppressLint
    -0.45
     AppCompat
    -0.44
    MLLoader
    -0.41
    ScopeManager
    -0.40
     ujednoznacz
    -0.37
    rosz
    -0.37
    AnchorTagHelper
    -0.37
    mallera
    -0.36
    testify
    -0.36
    ntag
    -0.36
    POSITIVE LOGITS
     obstacles
    2.31
     barriers
    2.27
     obstacle
    2.17
     barrier
    2.06
     Barriers
    1.93
    obstacles
    1.91
    Barriers
    1.89
     hurdles
    1.88
     impediments
    1.87
     obstáculos
    1.86
    Activations Density 0.664%

    No Known Activations