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

    Neuronpedia

    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. 13676
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific controversial viewpoint on having children

    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
    674
    +0.09
    0.3%
    836
    +0.07
    0.2%
    2008
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    836
    +0.09
    0.02
    709
    +0.07
    0.02
    1207
    +0.07
    0.02
    Negative Logits
     Gorb
    -0.70
     Rine
    -0.57
     Hecht
    -0.52
     kasa
    -0.52
     Knud
    -0.51
     Barbier
    -0.51
    $-$\\
    -0.50
     Hildebrand
    -0.50
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.50
     Schenk
    -0.49
    POSITIVE LOGITS
     paradiso
    0.63
     further
    0.56
    RenderAtEndOf
    0.54
     compleanno
    0.52
     furt
    0.51
     FURTHER
    0.51
    leggings
    0.51
     bacio
    0.51
     divertimento
    0.49
     step
    0.49
    Activations Density 0.165%

    No Known Activations