© 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 EvalsExportsinterp-engineNEWAPI 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. 16109
    Prev
    Next
    INDEX
    Explanations

    rare or uncommon elements, minerals, or occurrences

    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
    1077
    +0.13
    0.4%
    468
    +0.11
    0.4%
    214
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1077
    +0.13
    0.03
    869
    +0.11
    0.03
    517
    +0.10
    0.02
    Negative Logits
    AutoScaleMode
    -0.53
    IBOutlet
    -0.53
    IntoConstraints
    -0.52
    Personendaten
    -0.52
    DialogContent
    -0.50
    -------
    -0.48
     كومونز
    -0.47
     lccn
    -0.46
    lccn
    -0.46
    huriyet
    -0.45
    POSITIVE LOGITS
     ecru
    1.17
     hairc
    1.11
     embodi
    1.02
     swarovski
    1.00
     Rare
    0.98
     rarer
    0.97
     RARE
    0.97
     intersper
    0.93
     rare
    0.92
     nutella
    0.91
    Activations Density 0.104%

    No Known Activations