© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13842
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with leadership positions

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

    "Chief" followed by an executive position

    np_acts-logits-general · gemini-2.0-flash

    Chief followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.70
    tableFuture
    -0.65
    SBATCH
    -0.54
    WebControls
    -0.53
    principalTable
    -0.52
     proprement
    -0.51
    getItemId
    -0.50
     eighteenth
    -0.50
    mbic
    -0.50
     eighth
    -0.50
    POSITIVE LOGITS
     executive
    0.96
    tains
    0.84
     Executive
    0.84
    executive
    0.84
    tain
    0.82
    Executive
    0.76
     executives
    0.76
     Operating
    0.75
     EXECUTIVE
    0.73
     ejecutivo
    0.72
    Activations Density 0.068%

    No Known Activations