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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 6796
    Prev
    Next
    INDEX
    Explanations

    specific dates, age ranges, and numerical data related to time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日至
    -0.48
    thâu
    -0.47
    Personendaten
    -0.47
    LLocation
    -0.47
    setVerticalGroup
    -0.44
     mijne
    -0.43
    AppMethodBeat
    -0.42
    ſchen
    -0.40
    čina
    -0.40
     kuni
    -0.40
    POSITIVE LOGITS
     inclusive
    1.05
    inclusive
    0.93
    Inclusive
    0.75
     inclu
    0.72
     Inclusive
    0.67
     HasFactory
    0.65
     вклю
    0.60
     passim
    0.56
    CLUSIVE
    0.56
     inclus
    0.55
    Activations Density 0.734%

    No Known Activations