© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    details about complex tasks that require significant effort

    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
    +0.34
    1.3%
    876
    +0.09
    0.3%
    1531
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.34
    -0.04
    1257
    +0.09
    0.05
    2044
    +0.08
    0.09
    Negative Logits
    <bos>
    -2.61
     intersper
    -1.21
     endow
    -0.92
     shenan
    -0.89
     disbur
    -0.85
     enshr
    -0.84
     inaugurate
    -0.83
     vanqu
    -0.82
     encomp
    -0.80
     glimp
    -0.79
    POSITIVE LOGITS
     tricot
    0.91
     asado
    0.85
    gruntled
    0.83
     lavable
    0.82
     paradiso
    0.81
     bandung
    0.80
     lusso
    0.79
    vertisement
    0.77
     churrasco
    0.76
    astrous
    0.76
    Activations Density 1.211%

    No Known Activations