© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10945
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the phrase "no matter" along with related conditional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⅘
    -0.50
    -------
    -0.49
    Telefax
    -0.49
    WebElementEntity
    -0.46
     resourceCulture
    -0.45
     exactly
    -0.44
     justement
    -0.43
     Lijst
    -0.42
    henge
    -0.41
    exactly
    -0.41
    POSITIVE LOGITS
     whatever
    0.58
     whether
    0.58
     Whatever
    0.57
    Whatever
    0.53
    whatever
    0.52
    whether
    0.51
     Regardless
    0.50
    Regardless
    0.49
     apapun
    0.48
    imanapun
    0.48
    Activations Density 0.107%

    No Known Activations