© 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. 803
    Prev
    Next
    INDEX
    Explanations

    examples of technical terms and phrases related to information technology and medical procedures

    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
    845
    +0.10
    0.3%
    776
    +0.09
    0.3%
    1177
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    845
    +0.10
    0.05
    16
    +0.09
    0.07
    507
    +0.09
    0.04
    Negative Logits
    /');
    -0.58
    )]);
    -0.55
    ]")]
    -0.55
    =").
    -0.52
    /");
    -0.51
    ]");
    -0.51
    ").
    -0.50
    ");
    -0.49
    ]").
    -0.49
    ")));
    -0.48
    POSITIVE LOGITS
    Może
    0.66
     waer
    0.62
    Dziękuję
    0.61
     tupperware
    0.60
     bosch
    0.59
     thermomix
    0.58
     milf
    0.58
     overcrow
    0.58
     provence
    0.57
     stihl
    0.57
    Activations Density 0.743%

    No Known Activations