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. 16026
    Prev
    Next
    INDEX
    Explanations

    numbers or alphanumeric sequences

    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
    184
    +0.23
    0.8%
    764
    +0.21
    0.7%
    137
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.23
    0.06
    184
    +0.21
    0.03
    137
    +0.17
    0.06
    Negative Logits
    webElementXpaths
    -0.67
    tagHelperRunner
    -0.67
    tadır
    -0.63
    Попис
    -0.63
    UnusedPrivate
    -0.61
     betweenstory
    -0.61
     affitto
    -0.58
    PreferredItem
    -0.58
     lusso
    -0.58
    ArrowToggle
    -0.56
    POSITIVE LOGITS
     reconno
    0.72
    mainwindow
    0.72
     Whence
    0.68
     unlaw
    0.67
     Respectfully
    0.66
     apprehen
    0.66
     Incenti
    0.66
     actionTypes
    0.64
     unspeak
    0.64
     Wtf
    0.64
    Activations Density 0.388%

    No Known Activations