© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6757
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to identifying and addressing barriers and obstacles in various contexts

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

    Obstacles and barriers

    np_acts-logits-general · gemini-2.0-flash

    overcoming obstacles and barriers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vogt
    -0.41
    roek
    -0.40
     ans
    -0.40
    ⓧ
    -0.39
     T
    -0.39
    ซี
    -0.38
     se
    -0.38
    eken
    -0.36
    лтемелер
    -0.36
    ipedia
    -0.36
    POSITIVE LOGITS
     obstacles
    2.44
     obstacle
    2.17
     hurdles
    2.10
     barriers
    2.07
    obstacles
    2.00
     impediments
    1.92
     Barriers
    1.91
     obstáculos
    1.87
     hurdle
    1.85
    Obstacles
    1.84
    Activations Density 0.354%

    No Known Activations