© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11961
    Prev
    Next
    INDEX
    Explanations

    phrases expressing knowledge or certainty about a specific situation or belief

    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
    674
    +0.11
    0.3%
    1634
    +0.10
    0.3%
    489
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1634
    +0.11
    0.04
    2036
    +0.10
    0.04
    1183
    +0.10
    0.03
    Negative Logits
    Namara
    -0.56
    Millan
    -0.48
    Toole
    -0.47
    Leod
    -0.47
    farlane
    -0.47
     Watertown
    -0.44
    artney
    -0.44
    NameInMap
    -0.44
     Ashraf
    -0.44
    Cormack
    -0.43
    POSITIVE LOGITS
     ordina
    0.88
     doman
    0.82
     dispen
    0.77
     noss
    0.75
     milano
    0.75
     anse
    0.75
     noel
    0.75
     levis
    0.75
     lende
    0.73
     milla
    0.73
    Activations Density 0.120%

    No Known Activations