© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2402
    Prev
    Next
    INDEX
    Explanations

    expressions of love or strong positive emotions towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.3%
    605
    +0.13
    0.6%
    783
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.27
    0.04
    1892
    +0.13
    0.04
    783
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.66
    else
    -0.80
    public
    -0.79
    via
    -0.79
    <table>
    -0.77
    enumerate
    -0.77
    set
    -0.77
    </tbody>
    -0.77
    OneToMany
    -0.76
    static
    -0.76
    POSITIVE LOGITS
     maneu
    2.54
     impra
    2.39
     reluct
    2.33
     increa
    2.31
     accla
    2.29
     guarante
    2.29
     affor
    2.19
     stockholm
    2.18
     unden
    2.18
     scrat
    2.15
    Activations Density 0.107%

    No Known Activations