© 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. 2406
    Prev
    Next
    INDEX
    Explanations

    statements related to cultural or social attitudes, possibly regarding marriage rights or societal norms

    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
    872
    +0.10
    0.3%
    1108
    +0.09
    0.3%
    1131
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1004
    +0.10
    0.04
    1131
    +0.09
    0.04
    705
    +0.08
    0.03
    Negative Logits
     Juf
    -1.22
     Augu
    -1.15
     Keny
    -1.14
     volunte
    -1.09
     inev
    -1.08
     increa
    -1.07
     fte
    -1.07
     fta
    -1.07
     fup
    -1.06
     affor
    -1.03
    POSITIVE LOGITS
     unique
    1.00
    unique
    0.85
     different
    0.85
     differ
    0.83
    Unique
    0.83
     uniqueness
    0.82
     distinct
    0.82
     new
    0.80
     differs
    0.77
     Unique
    0.77
    Activations Density 0.637%

    No Known Activations