© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation or readiness for events or outcomes

    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
    1.6%
    1133
    +0.11
    0.5%
    1909
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.38
    0.03
    1909
    +0.11
    0.03
    1942
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.53
    <?
    -0.76
    ⓧ
    -0.64
    Base
    -0.56
    基
    -0.55
    public
    -0.55
    struct
    -0.55
    echo
    -0.54
    青
    -0.54
    base
    -0.54
    POSITIVE LOGITS
     affor
    1.24
     unlaw
    1.23
     lidl
    1.23
     bandung
    1.20
     eiffel
    1.15
     ecru
    1.13
     hilton
    1.09
     unwarran
    1.09
     shopee
    1.07
     mcdonald
    1.07
    Activations Density 0.155%

    No Known Activations