© 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. 6883
    Prev
    Next
    INDEX
    Explanations

    strong verbs and actions related to decision-making and political commentary

    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
    1392
    +0.14
    0.4%
    1678
    +0.11
    0.3%
    553
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.14
    0.08
    1129
    +0.11
    0.08
    1678
    +0.09
    0.05
    Negative Logits
     pamph
    -0.93
     reluct
    -0.92
     emphat
    -0.91
     desir
    -0.91
     inev
    -0.90
     unden
    -0.89
     toledo
    -0.89
     effe
    -0.88
     lidl
    -0.87
     disagre
    -0.87
    POSITIVE LOGITS
    醐
    0.65
     itong
    0.64
    MfG
    0.61
    ήσει
    0.60
    TintMode
    0.59
     saites
    0.58
    expandindo
    0.58
    Manbalar
    0.57
     numerus
    0.56
     trebui
    0.56
    Activations Density 0.796%

    No Known Activations