© 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. 6-RES-JB
    11. 4720
    Prev
    Next
    INDEX
    Explanations

    references related to geological events and medical conditions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    783
    +0.18
    1.0%
    313
    +0.17
    1.0%
    950
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.18
    0.05
    1343
    +0.17
    0.07
    1056
    +0.17
    0.05
    Negative Logits
    <bos>
    -1.13
     gratify
    -0.58
     appraise
    -0.57
     philosophic
    -0.54
    ίκη
    -0.54
     intersper
    -0.54
     poetical
    -0.52
     ardour
    -0.51
     calum
    -0.50
     recollect
    -0.50
    POSITIVE LOGITS
     balenciaga
    0.93
    capulco
    0.89
     prouve
    0.88
    dirond
    0.87
     prétend
    0.87
     rafra
    0.84
     Wh
    0.84
     Qu
    0.84
    arrings
    0.84
     surpl
    0.83
    Activations Density 0.616%

    No Known Activations