© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" in different contexts, especially those related to descriptions or attributes

    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
    +0.16
    0.6%
    1892
    +0.15
    0.6%
    699
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.16
    0.03
    120
    +0.15
    0.03
    32
    +0.13
    0.03
    Negative Logits
     Ayah
    -0.67
     roland
    -0.64
     manchester
    -0.64
     beverly
    -0.64
     suspic
    -0.63
     PLW
    -0.63
     encomp
    -0.63
     Mf
    -0.61
     increa
    -0.61
     reluct
    -0.61
    POSITIVE LOGITS
    <bos>
    0.73
    mistak
    0.65
    thinkable
    0.62
    relenting
    0.60
     Mémoires
    0.59
     Pièces
    0.56
    zegor
    0.56
    ruly
    0.55
    wavering
    0.55
     BioLib
    0.55
    Activations Density 0.168%

    No Known Activations