© 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. 1423
    Prev
    Next
    INDEX
    Explanations

    specific date and time references

    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
    +0.30
    1.0%
    1978
    +0.11
    0.4%
    1343
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.30
    0.09
    211
    +0.11
    0.07
    1108
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.66
     intersper
    -1.98
     encomp
    -1.70
     fta
    -1.68
     increa
    -1.65
     ecru
    -1.62
     hairc
    -1.61
     indestru
    -1.61
     thut
    -1.60
     ftu
    -1.57
    POSITIVE LOGITS
    ChatColor
    0.61
    CGRectMake
    0.60
    IBarButtonItem
    0.59
    URLEncoder
    0.59
    TypedValue
    0.59
     vinos
    0.58
    TextWatcher
    0.58
    MouseAdapter
    0.58
    TryParse
    0.58
    mousemove
    0.57
    Activations Density 0.265%

    No Known Activations