© 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. 0-GEMMASCOPE-RES-16K
    11. 8135
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly beaches, and appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     ſind
    -0.81
     myſelf
    -0.76
     kasarigan
    -0.72
     itſelf
    -0.70
     $_(
    -0.68
     ſever
    -0.68
     Diſ
    -0.66
     Reſ
    -0.65
     Houſe
    -0.65
     Monfieur
    -0.65
    POSITIVE LOGITS
     achievement
    0.46
     among
    0.46
    IntoConstraints
    0.42
     se
    0.40
     disposição
    0.40
     appointment
    0.38
     Mazz
    0.38
    1
    0.38
     arrangements
    0.37
     appointing
    0.37
    Activations Density 0.391%

    No Known Activations