Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15948
    Prev
    Next
    INDEX
    Explanations

    code-related terms related to memory management, specifically focusing on weak references and zeroing weak references

    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
    876
    +0.18
    0.5%
    1150
    +0.11
    0.3%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.18
    -0.00
    453
    +0.11
    0.04
    1030
    +0.10
    0.02
    Negative Logits
     organik
    -0.64
    UrlResolution
    -0.64
     elektronik
    -0.63
    cshtml
    -0.61
    SourceChecksum
    -0.61
     ekos
    -0.56
     optik
    -0.56
    elemField
    -0.55
    DockStyle
    -0.55
    msgTypes
    -0.55
    POSITIVE LOGITS
     affez
    1.28
     vespa
    1.26
     thermomix
    1.24
     lamborghini
    1.22
     casio
    1.20
     leonardo
    1.18
     michelin
    1.17
     scrat
    1.17
     yoda
    1.17
     gopro
    1.16
    Activations Density 0.300%

    No Known Activations