© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    terms related to laws, regulations, and cultural or religious sensitivities

    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
    184
    +0.26
    0.8%
    227
    +0.10
    0.3%
    1510
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.26
    0.02
    1984
    +0.10
    0.03
    227
    +0.09
    0.03
    Negative Logits
     embra
    -1.77
     effe
    -1.74
     dispen
    -1.70
     fte
    -1.69
     nece
    -1.68
     desir
    -1.68
     secon
    -1.66
     unce
    -1.63
     bordeaux
    -1.63
     unden
    -1.62
    POSITIVE LOGITS
    '
    0.62
    ’
    0.61
     itself
    0.59
    =""/>
    0.57
     stock
    0.55
     برابوك
    0.54
    (":");
    0.54
    ]!='
    0.54
     مكتبه
    0.53
    מעט
    0.53
    Activations Density 0.110%

    No Known Activations