© 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. 13403
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions

    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
    605
    +0.13
    0.5%
    1068
    +0.12
    0.4%
    1425
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.13
    0.03
    559
    +0.12
    0.03
    1276
    +0.11
    0.02
    Negative Logits
    Geld
    -0.47
     Sitten
    -0.47
     tiens
    -0.46
     prends
    -0.45
    обходи
    -0.44
     pourrais
    -0.43
    Prezzo
    -0.42
    ähkö
    -0.42
    Sess
    -0.42
    DAR
    -0.42
    POSITIVE LOGITS
     recommendation
    1.00
     Recommendation
    0.97
     recommendations
    0.96
     recommending
    0.96
     Recommend
    0.92
     recommend
    0.91
     Recommendations
    0.90
     recommended
    0.87
     Recommended
    0.87
     recommends
    0.86
    Activations Density 0.078%

    No Known Activations