© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    information related to software development, coding, and community discussions

    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
    1343
    +0.16
    0.5%
    1967
    +0.12
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.16
    0.03
    1062
    +0.12
    0.03
    782
    +0.09
    0.03
    Negative Logits
     unspeak
    -1.41
     shenan
    -1.40
     impra
    -1.34
     indescri
    -1.32
     intersper
    -1.32
     hairc
    -1.31
     disagre
    -1.29
     indestru
    -1.29
     gaily
    -1.28
     unden
    -1.26
    POSITIVE LOGITS
     utop
    0.94
     solidar
    0.89
     meras
    0.85
     asfal
    0.84
     ortop
    0.82
     ideolog
    0.78
     geolog
    0.78
     antropo
    0.76
     fras
    0.76
     marat
    0.75
    Activations Density 0.071%

    No Known Activations