© 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. 12541
    Prev
    Next
    INDEX
    Explanations

    connections between different concepts or ideas

    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
    1253
    +0.10
    0.3%
    468
    +0.09
    0.3%
    1082
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.10
    0.06
    137
    +0.09
    0.07
    468
    +0.08
    0.05
    Negative Logits
    <bos>
    -0.68
     réalise
    -0.51
     кӀ
    -0.51
    paravant
    -0.45
     vœ
    -0.44
     étu
    -0.41
     témoignage
    -0.41
    Abitanti
    -0.41
    ाहरण
    -0.40
    xtures
    -0.40
    POSITIVE LOGITS
    ?
    0.89
    ()?
    0.82
     ?</
    0.78
    ?</
    0.76
    ?
    0.76
    ?(
    0.76
    ?}
    0.76
    ?:
    0.76
    ؟
    0.75
    ?”
    0.74
    Activations Density 0.599%

    No Known Activations