© 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. 6741
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political and governmental issues

    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
    1177
    +0.17
    0.5%
    227
    +0.16
    0.5%
    678
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.17
    0.07
    1852
    +0.16
    0.05
    368
    +0.12
    0.05
    Negative Logits
    <bos>
    -0.97
    .
    -0.66
     [
    -0.65
    ↵↵
    -0.63
     (
    -0.63
    AccessLevel
    -0.63
    stdbool
    -0.63
    ↵
    -0.63
     —
    -0.62
    assertIn
    -0.61
    POSITIVE LOGITS
     dises
    1.49
     doman
    1.40
     tramont
    1.37
     Augu
    1.37
     sappi
    1.36
     parteci
    1.35
     suspic
    1.30
     revan
    1.28
     noss
    1.28
     sovere
    1.28
    Activations Density 0.658%

    No Known Activations