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. 18-GEMMASCOPE-RES-16K
    6. 8500
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "no matter" in various contexts

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

    "No matter how/what/who" phrases

    np_acts-logits-general · gemini-2.0-flash

    no matter how, regardless of

    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
    ✨:
    -0.85
     cref
    -0.69
    UnusedPrivate
    -0.66
     kaynağından
    -0.64
    RegistryLite
    -0.61
     ModelRenderer
    -0.60
    ioutil
    -0.60
    osoba
    -0.60
     Cæsar
    -0.59
     prostu
    -0.59
    POSITIVE LOGITS
     whether
    1.14
     how
    0.97
     apapun
    0.95
     whatsoever
    0.93
     whatever
    0.89
     Whether
    0.86
    whether
    0.84
    Whether
    0.83
     any
    0.81
     Whatever
    0.73
    Activations Density 0.063%

    No Known Activations