© 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. 28-GEMMASCOPE-RES-16K
    11. 4298
    Prev
    Next
    INDEX
    Explanations

    phrases related to going out or emerging from situations

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

    Followed by "in," "on," "and," "as," "of," or "with"

    np_acts-logits-general · gemini-2.0-flash

    comes out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithMany
    -0.38
     former
    -0.35
     вме
    -0.35
    countDown
    -0.34
     tasks
    -0.34
     progress
    -0.32
    <_>
    -0.32
    Squared
    -0.31
     reversing
    -0.30
    ANE
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.75
    ngdoc
    0.71
     فريبيس
    0.64
    RTEE
    0.63
    ConstraintMaker
    0.56
    MessageOf
    0.56
    ScopeManager
    0.55
    Cyfeiriadau
    0.54
    IsContent
    0.53
     smelling
    0.52
    Activations Density 0.141%

    No Known Activations