© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11582
    Prev
    Next
    INDEX
    Explanations

    words related to political or social movements

    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
    198
    +0.11
    0.3%
    1967
    +0.09
    0.3%
    1201
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1369
    +0.11
    0.02
    1201
    +0.09
    0.03
    919
    +0.09
    0.01
    Negative Logits
     encomp
    -0.65
    <_>
    -0.61
     kram
    -0.61
     quitted
    -0.61
     logis
    -0.60
     chanced
    -0.60
     intersper
    -0.56
     accla
    -0.55
    ">/
    -0.55
     hastened
    -0.55
    POSITIVE LOGITS
    deauna
    0.53
    prehensive
    0.52
     since
    0.50
     plong
    0.50
    ghijklmnop
    0.49
    Чыганаклар
    0.48
    depuis
    0.47
     réuss
    0.47
     různ
    0.47
     montr
    0.47
    Activations Density 0.965%

    No Known Activations