© 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. 4-GEMMASCOPE-RES-16K
    6. 12577
    Prev
    Next
    INDEX
    Explanations

    discussions of advantages and disadvantages associated with a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erialization
    -0.53
    ModelState
    -0.51
     Political
    -0.51
    şim
    -0.49
    contato
    -0.48
    MISSION
    -0.48
    Descriptor
    -0.47
    xsi
    -0.47
     vlas
    -0.47
    rebro
    -0.46
    POSITIVE LOGITS
    REASONS
    1.01
     advantages
    0.98
     REASONS
    0.91
    advantages
    0.90
    Vorteile
    0.89
     Advantages
    0.88
     voordelen
    0.88
    Benefits
    0.88
    Переваги
    0.87
    benefits
    0.87
    Activations Density 0.458%

    No Known Activations