© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    references to chronological order or steps in a process

    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
    781
    +0.08
    0.2%
    872
    +0.07
    0.2%
    1415
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.08
    0.02
    1836
    +0.07
    0.01
    451
    +0.07
    0.04
    Negative Logits
     praktik
    -0.73
     Áng
    -0.72
     alkoh
    -0.71
     kompati
    -0.66
     interse
    -0.64
     kollek
    -0.64
     kosme
    -0.64
     katastro
    -0.64
     Rumania
    -0.64
     konserv
    -0.62
    POSITIVE LOGITS
     first
    0.59
     firstly
    0.57
    Firstly
    0.57
     Firstly
    0.56
    首先
    0.56
     initial
    0.54
    先
    0.52
     basics
    0.52
     foremost
    0.51
     First
    0.50
    Activations Density 0.264%

    No Known Activations