© 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. 806
    Prev
    Next
    INDEX
    Explanations

    descriptions of software bugs and their statuses

    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
    876
    +0.17
    0.5%
    906
    +0.15
    0.5%
    50
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    594
    +0.17
    0.04
    100
    +0.15
    0.03
    736
    +0.11
    0.04
    Negative Logits
     hiperten
    -0.71
    <bos>
    -0.68
     Moines
    -0.68
     Biblia
    -0.68
     Obrador
    -0.67
    : 
    -0.66
     Irlanda
    -0.66
    cupa
    -0.65
    SharedDtor
    -0.65
     Palestina
    -0.64
    POSITIVE LOGITS
     encomp
    2.25
     indestru
    2.12
     intersper
    2.09
     disagre
    2.05
     impra
    2.03
     resear
    2.02
     embodi
    2.01
     suscep
    1.98
     maneu
    1.95
     increa
    1.95
    Activations Density 0.293%

    No Known Activations