© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    words related to software tools or product names

    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
    1757
    +0.07
    0.2%
    103
    +0.07
    0.2%
    1217
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.03
    1343
    +0.07
    0.08
    184
    +0.07
    0.03
    Negative Logits
     inso
    -0.87
     bamb
    -0.83
     snippetHide
    -0.80
     intest
    -0.79
     wein
    -0.78
     peculi
    -0.78
     pann
    -0.77
     anton
    -0.77
     ivi
    -0.77
     kram
    -0.74
    POSITIVE LOGITS
    BS
    1.18
     BS
    1.16
     postId
    0.86
     ficando
    0.85
     jsonString
    0.83
     resultList
    0.80
     Shakspeare
    0.79
     resultMap
    0.76
     companyId
    0.76
    <?
    0.73
    Activations Density 0.555%

    No Known Activations