© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1827
    Prev
    Next
    INDEX
    Explanations

    names of people or specific entities mentioned in a political context

    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
    394
    +0.13
    0.4%
    1919
    +0.12
    0.4%
    1741
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.13
    0.05
    1097
    +0.12
    0.04
    717
    +0.12
    0.03
    Negative Logits
     affez
    -1.12
     cioc
    -1.08
     thermomix
    -1.07
     frambo
    -1.05
     ananas
    -1.04
     libere
    -1.01
     poliester
    -1.01
     marrone
    -0.99
     persil
    -0.98
     chèvre
    -0.98
    POSITIVE LOGITS
     meanwhile
    0.84
     disagreed
    0.78
     responded
    0.75
     McLaugh
    0.73
     forestal
    0.71
     Concluding
    0.71
     reappeared
    0.70
     Whence
    0.70
     concluded
    0.70
     reconno
    0.69
    Activations Density 0.109%

    No Known Activations