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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14537
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, particularly those involving medical or ethical atrocities

    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
    509
    +0.13
    0.4%
    198
    +0.13
    0.4%
    1842
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.13
    0.07
    198
    +0.13
    0.06
    841
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.19
     lapto
    -0.83
     kram
    -0.75
     tyn
    -0.75
     krab
    -0.75
     kask
    -0.75
     fisk
    -0.73
     turist
    -0.70
     elek
    -0.70
     kras
    -0.70
    POSITIVE LOGITS
     shewn
    1.08
     unspeak
    0.97
     disagre
    0.96
     unwarran
    0.95
     increa
    0.93
     greate
    0.90
     indescri
    0.89
     Mejía
    0.89
     excru
    0.89
     indestru
    0.88
    Activations Density 0.599%

    No Known Activations