Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10494
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "no matter" as a way to denote resilience or disregard for obstacles

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

    "No matter what/where/how" phrases

    np_acts-logits-general · gemini-2.0-flash

    no matter what/where/how/who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.53
    VIAF
    -0.47
     cref
    -0.47
     stesso
    -0.46
    ならでは
    -0.45
    اریخ
    -0.44
    copg
    -0.44
    FactoryBean
    -0.43
    databind
    -0.43
     саме
    -0.42
    POSITIVE LOGITS
    Whoever
    0.80
     whoever
    0.79
     matter
    0.78
     Whatever
    0.78
     whether
    0.77
     whatever
    0.76
     Whoever
    0.76
    hichever
    0.75
    Whatever
    0.74
    osoever
    0.73
    Activations Density 0.068%

    No Known Activations