© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13764
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and characteristics of traits or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before words like "conclusion", "claim", or "desired."

    np_acts-logits-general · gemini-2.0-flash

    desired results or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BorderFactory
    -0.47
     onBind
    -0.46
    sono
    -0.45
    ంది
    -0.45
    ofold
    -0.42
     ligiloj
    -0.41
     }:
    -0.41
    ίναι
    -0.41
    ]._
    -0.41
     textStatus
    -0.41
    POSITIVE LOGITS
     desired
    2.39
    desired
    2.10
     Desired
    1.90
    Desired
    1.79
     wanted
    1.71
     gewünschten
    1.65
    wanted
    1.60
     gewüns
    1.60
     deseado
    1.47
     desirable
    1.46
    Activations Density 0.772%

    No Known Activations