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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 6-GEMMASCOPE-MLP-16K
    6. 119
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating the ability or possibility of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     صوتيه
    -0.73
    WriteBarrier
    -0.71
     дописавши
    -0.70
     PyLong
    -0.69
    XmlType
    -0.68
     esternos
    -0.68
    WriteAttribute
    -0.68
     BoxFit
    -0.68
     }{@
    -0.67
    GeneratedCode
    -0.66
    POSITIVE LOGITS
    %%
    0.48
     voelen
    0.48
     별
    0.47
    Builtin
    0.46
    ruptedException
    0.45
    /*!
    0.44
    本来
    0.44
     parlato
    0.44
    opcional
    0.44
     Default
    0.43
    Activations Density 0.473%

    No Known Activations