© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets related to software and technology setups

    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
    1177
    +0.14
    0.4%
    1445
    +0.13
    0.4%
    1967
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.14
    0.05
    1003
    +0.13
    0.02
    203
    +0.12
    0.03
    Negative Logits
    getLastName
    -0.60
     «
    -0.60
     “
    -0.56
    ]:
    -0.55
     „
    -0.54
     
    -0.52
     "
    -0.52
    「
    -0.52
    <eos>
    -0.52
     ‘
    -0.51
    POSITIVE LOGITS
     saluti
    1.15
     sappi
    1.14
     soggior
    1.13
     Luglio
    1.10
     quoique
    1.09
     appunt
    1.07
     simplif
    1.06
     Ottobre
    1.05
     scrat
    1.05
     parteci
    1.03
    Activations Density 0.195%

    No Known Activations