© 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. 36-GEMMASCOPE-RES-16K
    6. 7936
    Prev
    Next
    INDEX
    Explanations

    programming constructs and constructs related to the LLVM compiler framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.45
     beginnetje
    -0.44
    DockStyle
    -0.40
    kmale
    -0.38
     tslint
    -0.37
     macroscopic
    -0.36
     Pilate
    -0.35
     hormones
    -0.35
     macros
    -0.35
     mansions
    -0.34
    POSITIVE LOGITS
     llvm
    0.48
    AttributeSet
    0.48
     informée
    0.48
    llvm
    0.47
    insertBefore
    0.46
    EVT
    0.45
    spiller
    0.43
    IBOutlet
    0.43
    ,‎
    0.42
    GOTREF
    0.42
    Activations Density 0.652%

    No Known Activations