© 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. 12125
    Prev
    Next
    INDEX
    Explanations

    proper nouns and company names, possibly related to business and technology announcements

    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
    227
    +0.16
    0.5%
    453
    +0.14
    0.4%
    1177
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.06
    283
    +0.14
    0.02
    1177
    +0.13
    0.03
    Negative Logits
    <bos>
    -0.90
     thicken
    -0.53
    сутствие
    -0.52
     infected
    -0.51
     швидко
    -0.50
     ceva
    -0.49
     (
    -0.48
     чого
    -0.48
     intimidating
    -0.47
    但这
    -0.47
    POSITIVE LOGITS
     panik
    1.39
     silikon
    1.37
     alkoh
    1.30
     praktik
    1.27
     antik
    1.27
     kosme
    1.27
     keramik
    1.24
     seksi
    1.23
     karton
    1.23
     optik
    1.19
    Activations Density 0.276%

    No Known Activations