© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    texts related to political matters and government affairs

    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
    172
    +0.11
    0.3%
    147
    +0.10
    0.3%
    961
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.11
    0.02
    1417
    +0.10
    0.05
    1056
    +0.09
    0.06
    Negative Logits
     reluct
    -1.42
     emphat
    -1.30
     increa
    -1.29
     depic
    -1.28
     impra
    -1.27
     inev
    -1.26
     disagre
    -1.25
     affor
    -1.25
     indestru
    -1.23
     inconce
    -1.21
    POSITIVE LOGITS
    <bos>
    0.71
     other
    0.65
    also
    0.62
    other
    0.62
    aarrggbb
    0.60
     também
    0.59
     también
    0.59
     ALSO
    0.58
    También
    0.58
    Other
    0.57
    Activations Density 0.630%

    No Known Activations