© 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. 13833
    Prev
    Next
    INDEX
    Explanations

    topics related to miniseries and specific names of related entities such as "Minilogue."

    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
    1387
    +0.14
    0.6%
    1271
    +0.14
    0.6%
    971
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.14
    0.03
    892
    +0.14
    0.03
    1387
    +0.13
    0.03
    Negative Logits
    Havolalar
    -0.55
    iyor
    -0.51
    LEncoder
    -0.51
    yecek
    -0.47
    setOpaque
    -0.47
    アート
    -0.45
    assertNot
    -0.45
    leyici
    -0.45
    miyor
    -0.44
    ритори
    -0.43
    POSITIVE LOGITS
     Min
    1.23
    Min
    1.16
     MIN
    1.13
     min
    1.13
     Minis
    1.09
     miniatur
    1.07
    min
    1.06
     Minif
    1.02
     Mins
    1.01
     minig
    0.99
    Activations Density 0.094%

    No Known Activations