© 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. 2386
    Prev
    Next
    INDEX
    Explanations

    references to organizations, especially those related to governance or authority

    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
    1451
    +0.18
    0.7%
    596
    +0.15
    0.6%
    421
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1451
    +0.18
    0.03
    596
    +0.15
    0.02
    1910
    +0.14
    0.02
    Negative Logits
    الدراسه
    -0.58
    CONSIN
    -0.51
    fastjson
    -0.48
    UnusedPrivate
    -0.47
     وتسجيلات
    -0.46
     gynhyrchwyd
    -0.44
    makeConstraints
    -0.44
    JspWriter
    -0.44
    TextWatcher
    -0.44
     AssemblyCulture
    -0.44
    POSITIVE LOGITS
     Empire
    1.13
     empire
    1.13
     EMPIRE
    1.07
    Empire
    1.07
     imperial
    1.05
     Imperial
    1.03
     IMPER
    0.97
    empire
    0.95
    Imperial
    0.94
     empires
    0.94
    Activations Density 0.096%

    No Known Activations