© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7669
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating barriers or obstacles to progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.44
    SuppressLint
    -0.34
    AndEndTag
    -0.32
     irresponsible
    -0.32
    cipline
    -0.29
     AppCompat
    -0.29
    zeiro
    -0.29
    Bore
    -0.28
    Trama
    -0.28
    posób
    -0.28
    POSITIVE LOGITS
     barriers
    2.23
     obstacles
    2.22
     obstacle
    2.19
     barrier
    2.13
     impediments
    1.98
     Barriers
    1.96
     impediment
    1.94
    obstacles
    1.88
    barrier
    1.84
    Barriers
    1.84
    Activations Density 0.662%

    No Known Activations