© 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. 4307
    Prev
    Next
    INDEX
    Explanations

    technical terms related to research, science, and academic studies

    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
    2019
    +0.30
    1.0%
    1535
    +0.14
    0.5%
    381
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.30
    0.06
    924
    +0.14
    0.04
    1966
    +0.12
    0.03
    Negative Logits
     tupperware
    -0.82
     casio
    -0.82
     hentai
    -0.73
     logitech
    -0.71
     timelapse
    -0.66
     stickied
    -0.66
     gopro
    -0.66
     chibi
    -0.65
     gacha
    -0.65
     teflon
    -0.65
    POSITIVE LOGITS
    Although
    0.75
    While
    0.74
    When
    0.73
    Another
    0.70
    Before
    0.67
    There
    0.67
    As
    0.67
    Since
    0.67
    Instead
    0.67
    The
    0.66
    Activations Density 0.155%

    No Known Activations