© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2113
    Prev
    Next
    INDEX
    Explanations

    references to terms related to liberation or freedom

    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
    966
    +0.11
    0.3%
    1276
    +0.10
    0.3%
    410
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.04
    1363
    +0.10
    0.04
    1343
    +0.10
    0.04
    Negative Logits
    CPtr
    -0.80
     sarili
    -0.65
     bawat
    -0.65
    ACGIH
    -0.62
     maraming
    -0.59
    ValueStyle
    -0.58
     kanyang
    -0.58
     pagkak
    -0.56
    elemField
    -0.56
    cipline
    -0.55
    POSITIVE LOGITS
     Liber
    1.66
     Liberation
    1.63
    Liber
    1.50
    liber
    1.13
     liberation
    1.13
     liber
    1.05
     aen
    0.95
     vns
    0.93
     Roberts
    0.93
     fta
    0.93
    Activations Density 0.363%

    No Known Activations