© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    email-related information and discussion

    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
    50
    +0.20
    0.7%
    1741
    +0.07
    0.2%
    1265
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.20
    0.04
    1680
    +0.07
    0.04
    1188
    +0.06
    0.04
    Negative Logits
    <bos>
    -2.35
    /***
    -0.80
    ⓧ
    -0.79
     assiste
    -0.68
    💼
    -0.62
    intios
    -0.62
    //});
    -0.62
    equila
    -0.59
     reag
    -0.58
    lateinit
    -0.57
    POSITIVE LOGITS
     véhic
    0.97
     maneu
    0.84
     riva
    0.78
     catég
    0.77
     Khart
    0.74
     noyau
    0.74
     considér
    0.73
    uxx
    0.73
     epoca
    0.73
     pleins
    0.72
    Activations Density 0.062%

    No Known Activations