© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    terms related to quantitative analysis and methods

    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
    1557
    +0.08
    0.2%
    1048
    +0.07
    0.2%
    562
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.01
    1363
    +0.07
    0.02
    184
    +0.06
    0.01
    Negative Logits
    Și
    -0.67
    ⓧ
    -0.65
     metálica
    -0.64
    <bos>
    -0.61
    ENODEV
    -0.60
     Cruces
    -0.58
     wyg
    -0.57
    oarece
    -0.56
     rodeado
    -0.54
     lipca
    -0.54
    POSITIVE LOGITS
     quantitative
    2.38
     qualitative
    2.21
    quantitative
    2.20
     Quantitative
    2.20
    Quantitative
    2.12
     quantitatively
    2.02
     Qualitative
    1.96
    Qualitative
    1.87
     qualitatively
    1.74
     qualit
    1.45
    Activations Density 0.288%

    No Known Activations