© 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. 7165
    Prev
    Next
    INDEX
    Explanations

    quotes and statements related to politics and government

    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
    604
    +0.24
    0.7%
    764
    +0.13
    0.4%
    1253
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.24
    0.05
    921
    +0.13
    0.03
    1951
    +0.09
    0.03
    Negative Logits
    :,,
    -1.26
    <bos>
    -1.22
     NOO
    -1.18
     effe
    -1.17
     fuf
    -1.17
     ftu
    -1.16
     aen
    -1.13
     ?...
    -1.12
     ··
    -1.12
    <^
    -1.12
    POSITIVE LOGITS
    Pozri
    0.54
     hope
    0.51
    Життєпис
    0.48
    Handlung
    0.48
    Hélène
    0.48
    Comentários
    0.48
    ENODEV
    0.47
    Փ
    0.47
    wieś
    0.47
     tomorrow
    0.47
    Activations Density 0.309%

    No Known Activations