© 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. 2-GEMMASCOPE-RES-16K
    6. 8901
    Prev
    Next
    INDEX
    Explanations

    situations or concepts that involve tension or stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.45
     саны
    -0.40
     CURIAM
    -0.40
    スポンサーリンク
    -0.40
     SwitchCompat
    -0.39
    rieux
    -0.37
    haikusbot
    -0.37
    وانید
    -0.35
    ChildScrollView
    -0.35
     sebou
    -0.35
    POSITIVE LOGITS
     tension
    0.88
    Tension
    0.85
     Tension
    0.83
    tension
    0.79
    ira
    0.70
    setVerticalGroup
    0.64
    fjspx
    0.60
    AddTagHelper
    0.60
    IRA
    0.59
     "..\..\..\
    0.57
    Activations Density 0.558%

    No Known Activations