© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3949
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" in various contexts

    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
    +0.36
    1.5%
    1967
    +0.13
    0.5%
    752
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.36
    0.06
    1967
    +0.13
    0.06
    1334
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -1.01
    /**
    -0.79
    <?
    -0.77
     do
    -0.72
    RTLD
    -0.70
     and
    -0.70
     can
    -0.70
    ,
    -0.68
     don
    -0.68
    POSITIVE LOGITS
     reluct
    1.86
     lele
    1.83
     Juf
    1.79
     disagre
    1.75
     bandung
    1.75
     increa
    1.74
     jaya
    1.74
     fta
    1.74
     maneu
    1.72
     excru
    1.72
    Activations Density 0.297%

    No Known Activations