© 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. 2-GEMMASCOPE-RES-16K
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    concepts related to flexibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     szóci
    -0.52
     kasarigan
    -0.52
    Autoritní
    -0.46
     psicológica
    -0.42
     Dien
    -0.40
    NDA
    -0.40
     NLI
    -0.40
    addCriterion
    -0.40
    HMAC
    -0.40
    芥
    -0.40
    POSITIVE LOGITS
     flexibility
    0.63
     flexible
    0.60
     flexibilidad
    0.53
    addPreferredGap
    0.53
     lag
    0.53
    addContainerGap
    0.51
     Flexib
    0.51
    lite
    0.51
     Lag
    0.50
     Flexible
    0.50
    Activations Density 0.547%

    No Known Activations