© 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. 2-GEMMASCOPE-RES-16K
    6. 16231
    Prev
    Next
    INDEX
    Explanations

    quantitative references to groups or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rhosis
    -0.55
    ]));
    
    -0.50
    ):=\
    -0.49
    ><!--
    -0.47
     Ré
    -0.47
    ше
    -0.46
     cru
    -0.45
    >[]
    -0.44
    onomy
    -0.43
     rough
    -0.43
    POSITIVE LOGITS
     Majefty
    1.00
     himſelf
    0.90
     itſelf
    0.88
    DockStyle
    0.86
     themſelves
    0.85
     avoient
    0.85
     Roskov
    0.84
     myſelf
    0.84
     preſent
    0.79
     Monfieur
    0.79
    Activations Density 0.202%

    No Known Activations