© 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. 11-GEMMASCOPE-RES-16K
    6. 5355
    Prev
    Next
    INDEX
    Explanations

    words related to durability and resistance properties of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}")
    -0.55
     mapStateToProps
    -0.54
    OGND
    -0.52
    czaj
    -0.52
     Shaping
    -0.52
    atyw
    -0.49
    gesterone
    -0.49
    ientôt
    -0.48
    Diwedd
    -0.47
     getchar
    -0.47
    POSITIVE LOGITS
     durability
    0.96
     resilient
    0.83
     robustness
    0.81
     Durability
    0.80
     indestructible
    0.78
     durable
    0.76
     damage
    0.75
    Durability
    0.73
     resilience
    0.70
     tough
    0.69
    Activations Density 0.158%

    No Known Activations