© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 133
    Prev
    Next
    INDEX
    Explanations

    positive reviews and recommendations for a product

    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
    +0.37
    1.5%
    1013
    +0.15
    0.6%
    1403
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.37
    0.09
    1403
    +0.15
    0.02
    736
    +0.10
    0.06
    Negative Logits
    <bos>
    -1.81
    <s>
    -0.74
    <sup>
    -0.73
    <em>
    -0.72
    public
    -0.71
    <sub>
    -0.70
    ──
    -0.70
    <strong>
    -0.68
    ─
    -0.68
    DropColumn
    -0.68
    POSITIVE LOGITS
     shenan
    2.33
     accla
    2.18
     reluct
    2.09
     snoopy
    2.03
     indestru
    2.03
     sophistic
    2.02
     maneu
    2.02
     impra
    2.01
     disagre
    2.01
     unspeak
    1.97
    Activations Density 1.062%

    No Known Activations