© 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. 1853
    Prev
    Next
    INDEX
    Explanations

    words related to specific entities or names, potentially in the context of product descriptions, universities, or persons

    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
    1892
    +0.10
    0.3%
    994
    +0.09
    0.3%
    1372
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.08
    208
    +0.09
    0.06
    1597
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.75
    Hentet
    -0.63
     iprot
    -0.53
    StoryboardSegue
    -0.53
    ValueGenerated
    -0.52
    CopyWith
    -0.51
    IsOptional
    -0.49
    Пере
    -0.48
    ruptedException
    -0.47
    TintMode
    -0.47
    POSITIVE LOGITS
     depic
    1.27
     impra
    1.26
     guarante
    1.25
     fortn
    1.25
     reluct
    1.25
     increa
    1.24
     alre
    1.24
     affor
    1.24
     disagre
    1.23
     inev
    1.22
    Activations Density 0.673%

    No Known Activations