© 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 EvalsExportsinterp-engineNEWAPI 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. 4863
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical and cultural contexts

    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
    1156
    +0.13
    0.4%
    297
    +0.12
    0.4%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1156
    +0.13
    0.06
    297
    +0.12
    0.08
    2016
    +0.10
    0.07
    Negative Logits
    Lmfao
    -0.83
    Ehh
    -0.82
    FTFY
    -0.81
    Ikr
    -0.79
    Hahah
    -0.77
    Rgds
    -0.76
    Noice
    -0.71
    Lma
    -0.71
    Mhm
    -0.65
    Uhh
    -0.64
    POSITIVE LOGITS
     alike
    0.78
     respectively
    0.67
    respectively
    0.57
    IntoConstraints
    0.56
     respectivamente
    0.56
     respective
    0.49
     circulaire
    0.47
     fú
    0.46
    respective
    0.46
     serta
    0.45
    Activations Density 0.999%

    No Known Activations