© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    assertions and conclusions

    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
    382
    +0.19
    0.6%
    1535
    +0.17
    0.5%
    2034
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.19
    0.10
    1535
    +0.17
    0.06
    310
    +0.17
    0.04
    Negative Logits
     increa
    -2.65
     impra
    -2.54
     emphat
    -2.49
     affor
    -2.47
     maneu
    -2.46
     depic
    -2.44
     reluct
    -2.40
     encomp
    -2.38
     guarante
    -2.38
     inev
    -2.37
    POSITIVE LOGITS
     But
    1.81
    But
    1.68
     However
    1.66
    but
    1.61
     but
    1.57
    However
    1.55
     nhưng
    1.38
     BUT
    1.36
    BUT
    1.35
     however
    1.32
    Activations Density 0.415%

    No Known Activations