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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1-GEMMASCOPE-MLP-16K
    6. 8949
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or notation related to recurrence in a statistical or probabilistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$.
    -1.98
    )}$.
    -1.65
    }}$.
    -1.59
    })$.
    -1.52
    ]$.
    -1.50
     }}$.
    -1.46
    )$.
    -1.44
    |$.
    -1.41
    }$,
    -1.40
    \}$.
    -1.33
    POSITIVE LOGITS
    醛
    0.52
    amoan
    0.50
    [{
    0.49
    Palmar
    0.49
     Yearly
    0.48
     minimally
    0.47
     fleas
    0.46
     rū
    0.46
     soundly
    0.46
    完
    0.46
    Activations Density 0.138%

    No Known Activations