© 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. 15-GEMMASCOPE-RES-16K
    11. 1816
    Prev
    Next
    INDEX
    Explanations

    verbs indicating necessity, actions, or conditions related to obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.41
    bibfield
    -0.41
    ESSO
    -0.39
     préfé
    -0.38
     TestBed
    -0.38
    inginan
    -0.36
     ferner
    -0.35
     préf
    -0.35
    isFetching
    -0.35
    UserScript
    -0.34
    POSITIVE LOGITS
    expandindo
    0.65
    المناصب
    0.63
    Datuak
    0.56
    UIControlState
    0.55
    MLLoader
    0.54
     AssemblyCulture
    0.53
    ьаж
    0.52
    󠁣
    0.52
    OGND
    0.52
     Normdatei
    0.52
    Activations Density 0.754%

    No Known Activations