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

    Neuronpedia

    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. 13680
    Prev
    Next
    INDEX
    Explanations

    references to online communities or specific online platforms

    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
    1081
    +0.17
    0.5%
    1978
    +0.10
    0.3%
    321
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.17
    0.08
    1062
    +0.10
    0.07
    1705
    +0.08
    0.06
    Negative Logits
     unlaw
    -0.94
     gaily
    -0.90
     intersper
    -0.89
     fortn
    -0.88
     reconno
    -0.88
     increa
    -0.86
     affor
    -0.86
     apprehen
    -0.85
     purcha
    -0.85
     unwarran
    -0.84
    POSITIVE LOGITS
    Hauptartikel
    0.55
    ]=>
    0.54
    setVerticalGroup
    0.54
    fjspx
    0.53
    GORITH
    0.52
    ScopeManager
    0.50
    Clik
    0.50
    UObject
    0.49
     aapt
    0.49
    IRQn
    0.49
    Activations Density 0.490%

    No Known Activations