© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5600
    Prev
    Next
    INDEX
    Explanations

    timestamps and actions related to online gaming

    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
    1343
    +0.19
    0.6%
    453
    +0.10
    0.3%
    1967
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.19
    0.04
    981
    +0.10
    0.03
    801
    +0.10
    0.03
    Negative Logits
     intersper
    -1.28
     shenan
    -1.24
     disagre
    -1.24
     unspeak
    -1.22
     reluct
    -1.21
     maneu
    -1.18
     indescri
    -1.17
     snoopy
    -1.14
     hairc
    -1.14
     apprehen
    -1.14
    POSITIVE LOGITS
     solidar
    1.15
     alkoh
    1.01
     meras
    0.93
     utop
    0.92
     ortop
    0.89
     pól
    0.88
     geolog
    0.87
     kosme
    0.87
     elek
    0.86
     tragé
    0.85
    Activations Density 0.045%

    No Known Activations