© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    references to academic concepts, functions, or classifications related to various disciplines

    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
    1.1%
    1870
    +0.09
    0.4%
    2036
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2036
    +0.27
    0.06
    1652
    +0.09
    0.07
    2006
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.79
    ⓧ
    -0.75
    lateinit
    -0.71
    public
    -0.68
    contentLoaded
    -0.66
    Demografía
    -0.66
    。
    -0.65
    UnknownFieldSet
    -0.65
    protected
    -0.64
    }{||
    -0.64
    POSITIVE LOGITS
     affor
    1.80
     unlaw
    1.73
     impra
    1.67
     increa
    1.67
     unwarran
    1.60
     Juf
    1.60
     accla
    1.59
     fortn
    1.56
     disagre
    1.55
     excru
    1.55
    Activations Density 0.751%

    No Known Activations