© 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. 13908
    Prev
    Next
    INDEX
    Explanations

    phrases related to articles, grammar, and linguistic analysis

    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
    50
    +0.26
    0.9%
    1741
    +0.21
    0.7%
    2019
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.26
    0.06
    16
    +0.21
    0.07
    1967
    +0.14
    0.04
    Negative Logits
    <bos>
    -0.81
     shenan
    -0.72
     🤣🤣
    -0.72
     yoda
    -0.69
     milf
    -0.68
    igts
    -0.66
     lmfao
    -0.65
     Lmao
    -0.64
     firebaseConfig
    -0.63
     😭😭
    -0.63
    POSITIVE LOGITS
    Glej
    0.65
    Abraço
    0.62
    Obrigada
    0.59
    excelente
    0.59
    Secara
    0.58
    Mitä
    0.57
    Abraços
    0.56
    Adapun
    0.56
    Köszönöm
    0.55
    Hogyan
    0.54
    Activations Density 0.330%

    No Known Activations