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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14411
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues, political commentary, and community views

    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
    1842
    +0.24
    0.9%
    599
    +0.18
    0.6%
    468
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.24
    0.12
    599
    +0.18
    0.14
    1842
    +0.14
    0.10
    Negative Logits
    <bos>
    -1.37
    ⓧ
    -0.77
     pymysql
    -0.71
    
    -0.68
    Transcripción
    -0.66
    /***
    -0.66
    /**
    -0.65
    FTFY
    -0.65
    Hahah
    -0.65
    <?
    -0.63
    POSITIVE LOGITS
     gubern
    0.88
     monaster
    0.82
     sement
    0.79
     loto
    0.79
     centrif
    0.78
     cristian
    0.75
     marea
    0.73
     patria
    0.72
     tenda
    0.72
     merid
    0.71
    Activations Density 3.126%

    No Known Activations