© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 772
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to barriers and obstacles affecting progress and well-being

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

    limitation or obstruction

    np_acts-logits-general · gemini-2.0-flash

    hindering and limiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.59
    AndEndTag
    -0.48
    jsxFileName
    -0.48
    ⤹
    -0.47
    expose
    -0.47
    IPAC
    -0.47
    Scénario
    -0.46
     للمعارف
    -0.44
    ArgsConstructor
    -0.42
    Erstellt
    -0.42
    POSITIVE LOGITS
     hindering
    0.74
     hinders
    0.73
     hinder
    0.71
     hindered
    0.71
     impediment
    0.71
     hampered
    0.67
     impediments
    0.63
     impeded
    0.63
     impede
    0.63
     hindrance
    0.62
    Activations Density 0.777%

    No Known Activations