© 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. 17-GEMMASCOPE-RES-16K
    6. 6228
    Prev
    Next
    INDEX
    Explanations

    references to obstacles or hindrances 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 @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inama
    -0.52
     endowments
    -0.51
    حوالہ
    -0.49
    تماد
    -0.47
    setToolTipText
    -0.47
    momo
    -0.46
    foglio
    -0.46
    callee
    -0.45
     LoggerFactory
    -0.45
    addPreferredGap
    -0.45
    POSITIVE LOGITS
     impediment
    1.22
     obstacle
    1.17
     impediments
    1.17
     hindrance
    1.15
     obstruct
    1.13
     obstructing
    1.12
     obstacles
    1.11
     impede
    1.10
     obstruction
    1.09
     blocking
    1.09
    Activations Density 0.217%

    No Known Activations