© 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. 7416
    Prev
    Next
    INDEX
    Explanations

    mentions of social commentary, political discourse, and personal opinions

    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
    1735
    +0.12
    0.4%
    468
    +0.09
    0.3%
    261
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1735
    +0.12
    0.05
    261
    +0.09
    0.02
    1055
    +0.09
    0.04
    Negative Logits
     depic
    -1.83
     increa
    -1.79
     affor
    -1.67
     reluct
    -1.64
     emphat
    -1.64
     ?...
    -1.63
     guarante
    -1.61
     milf
    -1.61
     inev
    -1.61
     shenan
    -1.59
    POSITIVE LOGITS
    CompilerServices
    0.62
     happening
    0.60
    TypedValue
    0.60
    InteropServices
    0.60
    WireFormatLite
    0.57
     happen
    0.56
    RTEE
    0.56
    WindowManager
    0.55
    Xna
    0.54
     happens
    0.53
    Activations Density 0.503%

    No Known Activations