© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2046
    Prev
    Next
    INDEX
    Explanations

    phrases that express beliefs or hypotheses regarding incidents or situations

    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
    1.0%
    892
    +0.08
    0.3%
    184
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1356
    +0.27
    0.05
    100
    +0.08
    0.04
    971
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.27
    ⓧ
    -0.57
    #![
    -0.57
    public
    -0.52
    addComponent
    -0.51
     announced
    -0.51
    一
    -0.50
     announce
    -0.50
    afterEach
    -0.49
    foreach
    -0.48
    POSITIVE LOGITS
     affor
    1.29
     sovere
    1.21
     thut
    1.21
     maneu
    1.20
     Juf
    1.17
     increa
    1.16
     ?...
    1.16
     disagre
    1.16
     fta
    1.15
     embodi
    1.14
    Activations Density 0.597%

    No Known Activations