© 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. 2-GEMMASCOPE-RES-16K
    11. 4035
    Prev
    Next
    INDEX
    Explanations

    the word "Before" and its variations, indicating a focus on sequences or conditions preceding events

    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
    GTCX
    -0.61
    exitRule
    -0.60
    principalColumn
    -0.55
     bezeichneter
    -0.52
    transQ
    -0.51
    expandindo
    -0.51
    UVWXYZ
    -0.51
    aarrggbb
    -0.51
    ResumeLayout
    -0.50
     HFILL
    -0.50
    POSITIVE LOGITS
     before
    2.38
    before
    2.33
     Before
    2.27
    Before
    2.27
     BEFORE
    2.16
     antes
    2.14
    BEFORE
    2.06
     przed
    2.02
     перед
    1.93
     sebelum
    1.92
    Activations Density 0.326%

    No Known Activations