© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13550
    Prev
    Next
    INDEX
    Explanations

    references to stack-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
    
    -0.97
     gti
    -0.85
    ::_('
    -0.84
    esserung
    -0.83
     MotionEvent
    -0.80
     GTR
    -0.79
    ();?>
    -0.78
    tershire
    -0.78
     Belts
    -0.78
     nonUne
    -0.76
    POSITIVE LOGITS
     stacks
    1.40
     Stack
    1.40
     stack
    1.39
    Stack
    1.32
     STACK
    1.25
    stack
    1.22
     pile
    1.22
    STACK
    1.19
     Stacks
    1.18
     piles
    1.07
    Activations Density 0.148%

    No Known Activations