© 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. 1066
    Prev
    Next
    INDEX
    Explanations

    information related to albums and music nominations, as well as economic and productivity 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
    1978
    +0.17
    0.6%
    184
    +0.14
    0.5%
    50
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.01
    764
    +0.14
    0.01
    1510
    +0.13
    0.01
    Negative Logits
     robus
    -1.35
     meras
    -1.34
     cyr
    -1.27
     jep
    -1.27
     ohr
    -1.26
     makro
    -1.24
     incess
    -1.24
     ù
    -1.24
     gend
    -1.23
     solidar
    -1.22
    POSITIVE LOGITS
     unspeak
    0.81
     McLaugh
    0.78
     because
    0.68
     people
    0.67
     McInt
    0.66
     şeyi
    0.66
     Everybody
    0.64
     He
    0.63
     he
    0.63
     Because
    0.62
    Activations Density 0.049%

    No Known Activations