© 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. 11-GEMMASCOPE-RES-16K
    11. 10115
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "I said" along with its variations and associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.56
     surla
    -0.47
    artifactId
    -0.45
    $_['
    -0.43
     doPost
    -0.41
    
    -0.40
    UrlResolution
    -0.40
    mybatisplus
    -0.40
    ::_('
    -0.39
    agrid
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.63
     mentioned
    0.49
    mentioned
    0.44
     mencion
    0.42
     erwähnten
    0.42
     erwähnt
    0.42
     aforementioned
    0.41
    strokeStyle
    0.40
     nameless
    0.40
    anterior
    0.39
    Activations Density 0.328%

    No Known Activations