© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13474
    Prev
    Next
    INDEX
    Explanations

    terms related to the origins or sources of various concepts or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    971
    +0.11
    0.4%
    1865
    +0.11
    0.4%
    871
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1055
    +0.11
    0.02
    1246
    +0.11
    0.02
    971
    +0.10
    0.02
    Negative Logits
    Assista
    -0.59
    Conclusão
    -0.59
    Serviço
    -0.54
    Tener
    -0.52
    Importante
    -0.51
     ESPECIAL
    -0.49
    icionar
    -0.48
     TRAB
    -0.48
    Alguns
    -0.48
    Consumo
    -0.47
    POSITIVE LOGITS
     origins
    1.14
     origin
    1.13
     ORIGIN
    1.10
    origin
    1.06
     Origin
    1.01
     Origins
    1.00
    Origin
    0.98
    origins
    0.93
    Origins
    0.89
     originator
    0.88
    Activations Density 0.111%

    No Known Activations