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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 666
    Prev
    Next
    INDEX
    Explanations

    historical and political terms related to Georgia

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    596
    +0.10
    0.3%
    1092
    +0.07
    0.2%
    1492
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.04
    596
    +0.07
    0.02
    283
    +0.07
    0.01
    Negative Logits
     tayo
    -0.66
    owanej
    -0.61
     zależ
    -0.59
     spy
    -0.57
    ließlich
    -0.56
    owanego
    -0.56
     wią
    -0.55
    Iné
    -0.55
    owanym
    -0.55
     głównie
    -0.54
    POSITIVE LOGITS
    od
    2.54
    OD
    1.86
     Od
    1.82
    Od
    1.74
     OD
    1.54
     od
    1.48
    ods
    1.38
    odin
    1.22
     véhic
    1.19
    odat
    1.15
    Activations Density 0.201%

    No Known Activations