© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific journals and research articles

    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
    789
    +0.18
    0.7%
    1937
    +0.16
    0.6%
    313
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    789
    +0.18
    0.04
    313
    +0.16
    0.02
    1937
    +0.13
    0.03
    Negative Logits
     fte
    -0.69
     Docteur
    -0.69
     broderie
    -0.67
     fta
    -0.66
     velours
    -0.66
     fup
    -0.66
     effe
    -0.65
     fortn
    -0.64
     inev
    -0.63
     ftu
    -0.62
    POSITIVE LOGITS
     journal
    1.47
     Journal
    1.36
    Journal
    1.32
    journal
    1.31
     journals
    1.24
     JOURNAL
    1.07
    JOURNAL
    1.05
     Journals
    0.96
     journaling
    0.92
    journals
    0.81
    Activations Density 0.065%

    No Known Activations