© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    phrases related to genetic classification, racial awareness, and social value

    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
    674
    +0.11
    0.3%
    453
    +0.08
    0.2%
    1842
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.11
    0.04
    1919
    +0.08
    0.07
    862
    +0.08
    0.04
    Negative Logits
     encomp
    -1.39
     intersper
    -1.39
     increa
    -1.30
     strick
    -1.21
     Simult
    -1.20
     Intere
    -1.19
     reluct
    -1.19
     fortn
    -1.19
     philanth
    -1.19
     maneu
    -1.18
    POSITIVE LOGITS
    <bos>
    1.14
    把它
    0.80
     thereof
    0.72
     дописавши
    0.67
    将其
    0.65
     nó
    0.63
     بيها
    0.62
    对其
    0.62
     them
    0.61
     it
    0.57
    Activations Density 0.699%

    No Known Activations