© 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. 7703
    Prev
    Next
    INDEX
    Explanations

    technical terms related to the endocannabinoid system and its components

    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
    +0.19
    0.6%
    283
    +0.10
    0.3%
    1499
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.19
    0.03
    1809
    +0.10
    0.02
    520
    +0.09
    0.02
    Negative Logits
     soigneusement
    -0.81
    ształ
    -0.74
     Juventud
    -0.73
     regardant
    -0.70
     dicendo
    -0.69
     conçus
    -0.67
     kasarigan
    -0.67
     Alcalde
    -0.66
     spécialement
    -0.65
     Explora
    -0.65
    POSITIVE LOGITS
     meis
    0.91
     effe
    0.89
     aen
    0.88
     stik
    0.86
     ohr
    0.84
     „,
    0.83
     levis
    0.83
     fei
    0.82
     recept
    0.82
     plak
    0.82
    Activations Density 0.148%

    No Known Activations