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. 350
    Prev
    Next
    INDEX
    Explanations

    references to technology-related terms and events

    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
    856
    +0.16
    0.5%
    1499
    +0.12
    0.3%
    1445
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.16
    0.05
    1326
    +0.12
    0.03
    62
    +0.11
    0.03
    Negative Logits
    artamento
    -0.61
     tricot
    -0.58
     klok
    -0.53
     geforce
    -0.52
    quirrel
    -0.51
    ladiator
    -0.51
     @"";
    -0.50
     *++
    -0.50
    fiets
    -0.49
     brune
    -0.49
    POSITIVE LOGITS
    Referencie
    0.83
    Sklici
    0.77
    expandindo
    0.76
    Atsauces
    0.70
    Kjelder
    0.69
     Bekasi
    0.65
    Glej
    0.65
     estekak
    0.63
     Kese
    0.63
     sicura
    0.63
    Activations Density 0.214%

    No Known Activations