© 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. 3-GEMMASCOPE-RES-16K
    11. 5678
    Prev
    Next
    INDEX
    Explanations

    references to Facebook and related account management processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.36
    1
    -0.34
    0
    -0.30
     satunya
    -0.28
    se
    -0.27
    2
    -0.27
     estés
    -0.25
     bēr
    -0.25
    en
    -0.23
     hayas
    -0.23
    POSITIVE LOGITS
     queſta
    1.62
     ſta
    1.55
     myſelf
    1.48
     faſt
    1.47
    ſelf
    1.45
     pleaſure
    1.45
     ſte
    1.44
     ſche
    1.41
    [@BOS@]
    1.41
    <unused8>
    1.41
    Activations Density 0.439%

    No Known Activations