© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting film and cultural content

    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
    +0.38
    1.5%
    678
    +0.12
    0.5%
    198
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.38
    0.08
    198
    +0.12
    0.08
    51
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.59
    <?
    -0.78
    /**
    -0.76
    devServer
    -0.74
    GroupLayout
    -0.74
    ⓧ
    -0.73
    override
    -0.71
    /*
    -0.70
    HasIndex
    -0.68
    assertAll
    -0.65
    POSITIVE LOGITS
     impra
    1.73
     affor
    1.66
     accla
    1.65
     increa
    1.63
     reluct
    1.59
     maneu
    1.58
     practition
    1.53
     emphat
    1.52
     unden
    1.49
     uniqu
    1.48
    Activations Density 1.162%

    No Known Activations