© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    technical specifications of models, production variants, and equipment

    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
    +0.18
    0.6%
    1177
    +0.17
    0.5%
    1042
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.18
    0.06
    382
    +0.17
    0.05
    1042
    +0.17
    0.05
    Negative Logits
    <bos>
    -1.02
     ideolog
    -0.87
     utop
    -0.85
     solidar
    -0.82
     antropo
    -0.80
    GraphicsUnit
    -0.80
     revisor
    -0.80
     gubern
    -0.79
     alkoh
    -0.76
     melat
    -0.76
    POSITIVE LOGITS
     shenan
    1.68
     unspeak
    1.46
     impra
    1.42
     sophistic
    1.38
     hentai
    1.37
     indestru
    1.36
     uninten
    1.35
     snoopy
    1.35
     milf
    1.33
     disreg
    1.29
    Activations Density 0.546%

    No Known Activations