© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    statements related to societal issues, morality, politics, and ethical behavior

    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
    2034
    +0.14
    0.4%
    872
    +0.11
    0.3%
    1741
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.14
    0.07
    1959
    +0.11
    0.08
    310
    +0.11
    0.05
    Negative Logits
     solidar
    -0.82
     demen
    -0.81
     quí
    -0.81
     promi
    -0.80
     notor
    -0.80
     umo
    -0.80
     melat
    -0.79
     dises
    -0.79
     robus
    -0.76
     albic
    -0.76
    POSITIVE LOGITS
     Therefore
    0.73
     therefore
    0.71
    Therefore
    0.65
    therefore
    0.64
     Whether
    0.61
     Hence
    0.59
     whether
    0.58
     hence
    0.55
     unless
    0.52
     But
    0.52
    Activations Density 0.662%

    No Known Activations