© 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. 11222
    Prev
    Next
    INDEX
    Explanations

    terms related to political debates and current events

    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
    1870
    +0.15
    0.4%
    468
    +0.14
    0.4%
    764
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.15
    0.05
    468
    +0.14
    0.06
    868
    +0.12
    0.04
    Negative Logits
    <bos>
    -0.81
     voleva
    -0.76
     cammin
    -0.75
     scopri
    -0.74
     dimenti
    -0.72
     morire
    -0.70
     vorrei
    -0.70
     sappi
    -0.69
     faceva
    -0.68
     doveva
    -0.68
    POSITIVE LOGITS
     issues
    0.73
     matters
    0.67
     topics
    0.67
     vexed
    0.65
     versus
    0.60
     topic
    0.59
     pamph
    0.58
     possibilities
    0.57
     dangers
    0.57
     problems
    0.57
    Activations Density 0.812%

    No Known Activations