© 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. 13882
    Prev
    Next
    INDEX
    Explanations

    instances of missing or forgetting something but not being overly bothered by it

    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
    1233
    +0.12
    0.4%
    678
    +0.09
    0.3%
    874
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.12
    0.04
    1166
    +0.09
    0.03
    757
    +0.09
    0.03
    Negative Logits
    Appellee
    -0.56
    PDF
    -0.52
     بيها
    -0.51
    MENAFN
    -0.50
    alog
    -0.48
    oredCriteria
    -0.48
    ategy
    -0.48
    joueurs
    -0.46
    Affirmed
    -0.46
    indeer
    -0.46
    POSITIVE LOGITS
     shenan
    1.17
     secon
    1.15
     opport
    1.14
     Missed
    1.12
     uninten
    1.12
     reluct
    1.10
     seiz
    1.10
     depic
    1.09
     inev
    1.09
     maneu
    1.08
    Activations Density 0.120%

    No Known Activations