© 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. 2407
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and configuration setup

    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
    137
    +0.13
    0.4%
    1224
    +0.12
    0.4%
    994
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.13
    0.05
    1786
    +0.12
    0.00
    584
    +0.09
    0.02
    Negative Logits
     Administrativna
    -0.72
    MessageTagHelper
    -0.65
     gradova
    -0.61
    Solución
    -0.59
    كويكب
    -0.56
    DataAnnotations
    -0.55
     senderismo
    -0.54
     patin
    -0.53
    Espèce
    -0.52
    intios
    -0.52
    POSITIVE LOGITS
     impra
    0.93
     unve
    0.86
     embodi
    0.86
     indestru
    0.86
     shenan
    0.83
     friable
    0.82
     hairc
    0.82
     disreg
    0.82
     encomp
    0.79
     scrat
    0.78
    Activations Density 0.281%

    No Known Activations