© 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. 0-GEMMASCOPE-RES-16K
    11. 7380
    Prev
    Next
    INDEX
    Explanations

    terms related to partnerships and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.89
    MigrationBuilder
    -0.84
    ########.
    -0.79
    oplayer
    -0.74
    contentLoaded
    -0.71
    Datuak
    -0.67
    RetentionPolicy
    -0.65
     ComVisible
    -0.65
    BeginContext
    -0.65
    parsedMessage
    -0.64
    POSITIVE LOGITS
     Partners
    1.12
    Partners
    1.08
     Partner
    0.98
    Partner
    0.95
     PARTNERS
    0.95
     Partnership
    0.92
    partner
    0.90
     partnerships
    0.90
    partners
    0.89
     Partnerships
    0.88
    Activations Density 0.138%

    No Known Activations