© 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. 33-GEMMASCOPE-RES-16K
    11. 10912
    Prev
    Next
    INDEX
    Explanations

    information related to demographic statistics and participants in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -1.00
     estekak
    -1.00
    GEBURTSDATUM
    -0.96
    évaluateur
    -0.95
    LookAnd
    -0.94
     ProtoMessage
    -0.94
    NameInMap
    -0.94
    featureID
    -0.93
     CreateTagHelper
    -0.93
    expandindo
    -0.92
    POSITIVE LOGITS
     муниципа
    0.29
     sms
    0.29
     Lidl
    0.28
    parametrize
    0.28
     plots
    0.28
     sports
    0.28
     euro
    0.27
     pension
    0.27
     sm
    0.27
     €
    0.26
    Activations Density 0.517%

    No Known Activations