© 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. 0-GEMMASCOPE-RES-16K
    11. 1541
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "forum" and discussions related to it

    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
    作
    -0.48
    ck
    -0.41
    AS
    -0.41
    ❈
    -0.40
    pang
    -0.40
     Estación
    -0.39
    URL
    -0.39
     الف
    -0.38
    ÁCT
    -0.38
    Rifer
    -0.37
    POSITIVE LOGITS
    Discussions
    1.13
    Discussion
    1.10
     Discussions
    1.09
     Discussion
    1.05
    discussions
    1.00
     discussions
    1.00
    discussion
    0.97
     DISCUSSION
    0.96
    DISCUSSION
    0.94
     discussion
    0.93
    Activations Density 0.302%

    No Known Activations