© 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. 6718
    Prev
    Next
    INDEX
    Explanations

    percentages and statistics related to public figures and political opinions

    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
    381
    +0.10
    0.3%
    205
    +0.09
    0.3%
    184
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.10
    0.04
    972
    +0.09
    0.03
    1244
    +0.09
    0.03
    Negative Logits
     §.
    -0.87
     Sert
    -0.86
     Penna
    -0.83
     mikrofon
    -0.82
     Mémoires
    -0.81
     marte
    -0.81
     aquarelle
    -0.81
     wien
    -0.80
     Confe
    -0.80
     Román
    -0.80
    POSITIVE LOGITS
     compares
    0.61
     roughly
    0.59
     staggering
    0.59
     impressive
    0.58
     statistically
    0.56
     statistic
    0.56
     hardly
    0.56
     translates
    0.55
     pretty
    0.55
     exceeds
    0.55
    Activations Density 0.212%

    No Known Activations