© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13054
    Prev
    Next
    INDEX
    Explanations

    descriptive words expressing powerful, surprising, or impressive qualities

    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
    1056
    +0.14
    0.5%
    1272
    +0.12
    0.4%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.14
    0.06
    468
    +0.12
    0.05
    1272
    +0.11
    0.04
    Negative Logits
     pério
    -0.63
     kompati
    -0.55
     trö
    -0.55
    CppMethod
    -0.53
     célé
    -0.52
     mikrofon
    -0.51
     kompon
    -0.51
    adhy
    -0.50
     ilang
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
     jsonString
    0.71
    ingly
    0.70
    ly
    0.66
     newArr
    0.65
     accountId
    0.64
     itemName
    0.63
     imagePath
    0.61
     nmax
    0.61
     noOf
    0.59
    mazing
    0.58
    Activations Density 0.214%

    No Known Activations