© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12488
    Prev
    Next
    INDEX
    Explanations

    references to future developments and expectations

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

    preceding "coming" or related to future events

    np_acts-logits-general · gemini-2.0-flash

    future coming events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.49
     ModelExpression
    -0.43
    DebuggerNonUser
    -0.42
    uxxxx
    -0.38
    homonymie
    -0.38
     שוליים
    -0.37
    autorest
    -0.37
    tagHelperRunner
    -0.37
     Sir
    -0.36
    ंदीखरीदारी
    -0.35
    POSITIVE LOGITS
     coming
    1.05
     forthcoming
    0.98
    coming
    0.98
    Coming
    0.95
     COMING
    0.93
     upcoming
    0.88
     Coming
    0.88
     kommenden
    0.85
    COMING
    0.81
    upcoming
    0.80
    Activations Density 0.162%

    No Known Activations