© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 603
    Prev
    Next
    INDEX
    Explanations

    occurrences 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
    +0.33
    1.5%
    752
    +0.12
    0.5%
    1624
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.33
    0.06
    1034
    +0.12
    0.05
    401
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.86
    ⓧ
    -1.01
    /**
    -0.84
    BeginInit
    -0.78
     createState
    -0.73
    SystemColors
    -0.71
    HasColumnType
    -0.71
    PageRoute
    -0.71
     Walkover
    -0.70
    <?
    -0.70
    POSITIVE LOGITS
     increa
    1.72
     Juf
    1.67
     maneu
    1.66
     affor
    1.65
     reluct
    1.62
     bandung
    1.55
     inev
    1.54
     secon
    1.54
     volunte
    1.54
     accla
    1.53
    Activations Density 0.224%

    No Known Activations