© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14464
    Prev
    Next
    INDEX
    Explanations

    sentences containing direct quotes

    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
    1577
    +0.30
    1.2%
    1842
    +0.29
    1.2%
    394
    +0.28
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.30
    0.09
    1577
    +0.29
    0.11
    1108
    +0.28
    0.10
    Negative Logits
     encomp
    -0.81
     Khart
    -0.81
     fortn
    -0.78
     reluct
    -0.76
     ineffec
    -0.76
     Bartholo
    -0.75
     unlaw
    -0.73
     renfer
    -0.72
     prerog
    -0.72
     Rine
    -0.71
    POSITIVE LOGITS
    <bos>
    0.99
    MessageTagHelper
    0.65
     betweenstory
    0.58
    RegressionTest
    0.51
     incomplète
    0.51
    AndEndTag
    0.49
     himo
    0.49
     Éditions
    0.49
     mús
    0.48
    parsedMessage
    0.47
    Activations Density 1.685%

    No Known Activations