© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5444
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between individuals and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambién
    -0.53
    Cyfeiriadau
    -0.50
     contextLoads
    -0.48
     lisäksi
    -0.45
    virano
    -0.42
     acabados
    -0.40
     INTERESAR
    -0.39
     calcetines
    -0.39
     kysy
    -0.39
     فريبيس
    -0.38
    POSITIVE LOGITS
     mans
    1.21
     childs
    1.17
     governments
    1.16
     Governments
    1.16
     peoples
    1.13
     compan
    1.08
     nations
    1.06
     suns
    1.05
     earths
    1.00
     publics
    1.00
    Activations Density 0.500%

    No Known Activations