© 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. 6475
    Prev
    Next
    INDEX
    Explanations

    references to political and investigative actions

    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
    468
    +0.17
    0.5%
    776
    +0.11
    0.4%
    50
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.17
    0.07
    316
    +0.11
    0.06
    332
    +0.11
    0.05
    Negative Logits
     !...
    -1.14
     tremb
    -1.12
     »>
    -1.11
     dises
    -1.11
     wien
    -1.11
     appunt
    -1.09
     thut
    -1.08
     ?...
    -1.07
     estrema
    -1.06
     aen
    -1.06
    POSITIVE LOGITS
     particular
    0.86
     situation
    0.82
     phenomenon
    0.71
     topic
    0.67
     issue
    0.66
     scenario
    0.64
     aspect
    0.64
     matter
    0.62
    .
    0.61
     type
    0.61
    Activations Density 0.214%

    No Known Activations