© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2516
    Prev
    Next
    INDEX
    Explanations

    words related to solving mysteries and cryptic puzzles

    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
    468
    +0.07
    0.2%
    1898
    +0.07
    0.2%
    1324
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.07
    0.05
    284
    +0.07
    0.06
    1000
    +0.07
    0.02
    Negative Logits
     unden
    -1.36
     inev
    -1.34
     ?...
    -1.29
     inder
    -1.25
     increa
    -1.23
     intere
    -1.23
     fep
    -1.22
     dispen
    -1.22
     secon
    -1.20
     embra
    -1.20
    POSITIVE LOGITS
    oredCriteria
    0.69
     by
    0.69
    <bos>
    0.65
     efficiently
    0.61
     quickly
    0.61
     ולה
    0.58
     using
    0.57
     effectively
    0.57
     via
    0.57
     while
    0.56
    Activations Density 0.464%

    No Known Activations