© 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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12776
    Prev
    Next
    INDEX
    Explanations

    technical terms and explanations within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1577
    +0.28
    1.0%
    674
    +0.25
    0.9%
    1870
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.28
    0.02
    1577
    +0.25
    0.16
    1265
    +0.16
    0.06
    Negative Logits
     reluct
    -1.88
     shenan
    -1.82
     unspeak
    -1.80
     pamph
    -1.75
     apprehen
    -1.74
     intersper
    -1.71
     disagre
    -1.69
     unlaw
    -1.65
     Abbé
    -1.63
     sophistic
    -1.58
    POSITIVE LOGITS
    <bos>
    1.30
    octanol
    0.71
     jScrollPane
    0.67
     consultato
    0.65
     NSCoder
    0.64
    parsedMessage
    0.64
    ─
    0.64
     utafitiHapana
    0.63
    AutoScaleMode
    0.62
     disambiguazione
    0.62
    Activations Density 4.942%

    No Known Activations