© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    mentions of the importance or lack of importance of religion in daily life

    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
    1553
    +0.09
    0.3%
    605
    +0.08
    0.2%
    453
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.09
    0.04
    1714
    +0.08
    0.03
    605
    +0.07
    0.01
    Negative Logits
     disagre
    -1.16
     indestru
    -1.12
     inconce
    -1.07
     Messieurs
    -1.04
     Souha
    -1.04
     malheureux
    -1.03
     depic
    -1.03
     unspeak
    -1.03
     encomp
    -1.02
     Shakspeare
    -0.98
    POSITIVE LOGITS
    medium
    0.65
     moderate
    0.63
     medium
    0.62
     moderately
    0.58
    Solución
    0.54
    moderate
    0.53
     intermediate
    0.52
    permitAll
    0.51
     elit
    0.49
     normal
    0.49
    Activations Density 0.314%

    No Known Activations