© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 46890
    Prev
    Next
    INDEX
    Explanations

    logical statements and programming-related conditions

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

    restarting test actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     justement
    -0.42
    .*")]
    -0.40
    Filmografie
    -0.37
    enterOuterAlt
    -0.34
    }))
    
    -0.33
    newArrayList
    -0.33
    resizingMask
    -0.33
    ENODEV
    -0.33
     uLocal
    -0.32
     ddelweddau
    -0.32
    POSITIVE LOGITS
     restart
    0.73
     test
    0.72
     reboot
    0.68
     testing
    0.66
     refresh
    0.62
     tested
    0.61
     Test
    0.61
     rerun
    0.58
    Test
    0.58
     Refresh
    0.57
    Activations Density 0.059%

    No Known Activations