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

    Neuronpedia

    Jacobian LensNEW
    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. 11543
    Prev
    Next
    INDEX
    Explanations

    mentions of racial identity, segregation, and social justice issues related to the Black community

    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
    1978
    +0.16
    0.5%
    1385
    +0.14
    0.4%
    1984
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.06
    1984
    +0.14
    0.06
    1510
    +0.10
    0.04
    Negative Logits
    ьаж
    -0.72
     disambiguazione
    -0.71
    rungsseite
    -0.71
    تقاوى
    -0.70
     kasarigan
    -0.69
    #+#
    -0.69
    StoreMessageInfo
    -0.69
     &___
    -0.66
    GEBURTSDATUM
    -0.66
     informée
    -0.64
    POSITIVE LOGITS
     Augu
    1.42
     Simult
    1.40
     Godt
    1.35
     Juf
    1.34
     Whence
    1.29
     Khart
    1.29
     Sinal
    1.29
     sergio
    1.27
     Intere
    1.27
     fta
    1.27
    Activations Density 0.248%

    No Known Activations