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

    Neuronpedia

    Jacobian LensNEW
    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. 14773
    Prev
    Next
    INDEX
    Explanations

    -information related to social issues like healthcare, women's rights, and food safety

    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
    651
    +0.08
    0.2%
    1062
    +0.08
    0.2%
    394
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.08
    0.04
    394
    +0.08
    0.06
    651
    +0.08
    0.04
    Negative Logits
     aquare
    -0.88
     stoff
    -0.84
     franz
    -0.84
     affez
    -0.84
     perle
    -0.83
     marte
    -0.83
     fluo
    -0.80
     ananas
    -0.80
     quí
    -0.78
     persil
    -0.78
    POSITIVE LOGITS
     occurs
    0.89
     isn
    0.89
     is
    0.84
     happens
    0.81
     seems
    0.81
     wasn
    0.80
     abounds
    0.79
     becomes
    0.78
     tends
    0.78
     has
    0.77
    Activations Density 0.508%

    No Known Activations