© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    descriptions of various features or actions within a context, often involving chronological details

    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
    394
    +0.17
    0.5%
    50
    +0.14
    0.4%
    1166
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.17
    0.14
    496
    +0.14
    0.04
    752
    +0.09
    0.06
    Negative Logits
    ）.
    -0.88
    '].
    -0.82
    "].
    -0.81
    ']).
    -0.79
    ])).
    -0.76
    /}.
    -0.76
    ").
    -0.75
    ').
    -0.75
    "]).
    -0.74
    ].
    -0.74
    POSITIVE LOGITS
     affor
    1.20
     Juf
    1.20
     impra
    1.19
     squa
    1.19
     jurassic
    1.17
     fta
    1.16
     invin
    1.14
     aen
    1.14
     Augu
    1.14
     increa
    1.14
    Activations Density 2.463%

    No Known Activations