© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7357
    Prev
    Next
    INDEX
    Explanations

    details related to the design and mechanics of in-game boss battles

    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
    856
    +0.17
    0.5%
    764
    +0.15
    0.5%
    599
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.17
    0.07
    16
    +0.15
    0.10
    678
    +0.12
    0.08
    Negative Logits
     Michoacán
    -0.75
     Walkover
    -0.69
    IsContent
    -0.68
    prnewswire
    -0.67
     CreateTagHelper
    -0.65
    Искәрмәләр
    -0.63
     sement
    -0.62
     hiperten
    -0.60
    ]--;
    -0.60
    ScopeManager
    -0.60
    POSITIVE LOGITS
     clô
    1.01
     vété
    0.96
     considér
    0.92
     Potenti
    0.91
     supplé
    0.91
     embodi
    0.90
     Ename
    0.90
     mémor
    0.89
     confé
    0.89
     habile
    0.89
    Activations Density 1.368%

    No Known Activations