© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and processes

    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
    876
    +0.21
    0.7%
    752
    +0.13
    0.4%
    283
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.21
    0.05
    736
    +0.13
    0.05
    283
    +0.11
    0.01
    Negative Logits
     demurrer
    -0.78
     Republics
    -0.75
     scritta
    -0.69
     titulada
    -0.67
    _'.$
    -0.66
     storica
    -0.65
     Whigs
    -0.65
    /#{
    -0.65
     vestiti
    -0.64
     imprimée
    -0.64
    POSITIVE LOGITS
     effe
    1.61
     „,
    1.60
     aen
    1.57
     meis
    1.51
     plak
    1.50
     fup
    1.48
     mef
    1.43
     myn
    1.39
     inder
    1.37
     ohr
    1.36
    Activations Density 0.232%

    No Known Activations