© 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. 7009
    Prev
    Next
    INDEX
    Explanations

    solutions or plans in geopolitical contexts

    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
    1965
    +0.11
    0.3%
    1533
    +0.10
    0.3%
    919
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.11
    0.05
    919
    +0.10
    0.03
    455
    +0.09
    0.02
    Negative Logits
     trico
    -0.94
     Keny
    -0.86
     Sted
    -0.86
     persil
    -0.84
     Perci
    -0.84
     Middles
    -0.84
     Knud
    -0.83
     dises
    -0.83
     Lyd
    -0.82
     fluo
    -0.82
    POSITIVE LOGITS
     includes
    0.65
     exists
    0.62
     existed
    0.60
     comes
    0.59
     include
    0.58
     gerekiyor
    0.57
     tevens
    0.56
     aplican
    0.56
     happens
    0.55
     niečo
    0.55
    Activations Density 0.333%

    No Known Activations