© 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. 2948
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to polling and public opinion

    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
    +0.13
    0.4%
    453
    +0.08
    0.2%
    1978
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.13
    0.04
    1182
    +0.08
    0.03
    776
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.54
     AssemblyCompany
    -0.58
     modernize
    -0.57
    },{
    -0.56
    BeginInit
    -0.56
    DebuggerNonUser
    -0.55
    xhttp
    -0.55
    <!--
    -0.54
    toPromise
    -0.54
    ByUrl
    -0.52
    POSITIVE LOGITS
     maske
    1.28
     labd
    1.20
     brune
    1.15
     kafe
    1.14
     seksi
    1.13
     saar
    1.12
     lele
    1.09
     optik
    1.08
     „,
    1.06
     Præ
    1.06
    Activations Density 0.093%

    No Known Activations