© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110093
    Prev
    Next
    INDEX
    Explanations

    terms related to "tilde" or modified variables in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    widetilde
    -1.30
    geqslant
    -0.57
    leqslant
    -0.54
    widehat
    -0.54
    overline
    -0.43
    bigsqcup
    -0.40
    varrho
    -0.38
    triangleright
    -0.37
    Descripcion
    -0.36
    FontAwesome
    -0.35
    POSITIVE LOGITS
     ब्रेकडाउन
    0.65
     '\\;'
    0.63
     ddelweddau
    0.60
    TypedDataSet
    0.60
     مرئيه
    0.57
    舺
    0.57
    ⟬
    0.57
    RTCK
    0.56
    MENAFN
    0.55
    <unused74>
    0.54
    Activations Density 0.010%

    No Known Activations