© 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. 8712
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Dean"

    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
    1376
    +0.14
    0.8%
    1145
    +0.14
    0.8%
    1964
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.14
    0.02
    1145
    +0.14
    0.02
    1964
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.41
    char
    -0.63
    int
    -0.62
    string
    -0.61
    public
    -0.60
    lateinit
    -0.59
    ve
    -0.58
    export
    -0.58
     invest
    -0.57
    local
    -0.57
    POSITIVE LOGITS
     DEAN
    1.52
     Minang
    1.47
     Dean
    1.39
     dises
    1.37
    Dean
    1.34
     unwarran
    1.33
     unlaw
    1.32
     increa
    1.32
     Juf
    1.31
     saar
    1.29
    Activations Density 0.139%

    No Known Activations