© 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
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 2240
    Prev
    Next
    INDEX
    Explanations

    references to emotional or physical challenges faced by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.48
    TypedDataSet
    -0.46
     GenerationType
    -0.45
    RTCK
    -0.45
    GIVEREF
    -0.44
     jspb
    -0.43
    __(/*!
    -0.43
    ביוגרפיה
    -0.42
    LookAnd
    -0.40
    cookieParser
    -0.40
    POSITIVE LOGITS
     distraction
    1.50
     distracted
    1.44
     distractions
    1.38
     Distra
    1.33
     distra
    1.27
     distracting
    1.22
     distract
    1.17
     concentration
    1.14
     concentrating
    1.06
     Concentration
    1.04
    Activations Density 0.436%

    No Known Activations