© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3759
    Prev
    Next
    INDEX
    Explanations

    instances of someone serving in a political or legal capacity, such as holding a position in court or government

    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
    703
    +0.13
    0.5%
    1624
    +0.13
    0.4%
    1937
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.13
    0.04
    1096
    +0.13
    0.03
    1937
    +0.12
    0.03
    Negative Logits
    Erik
    -0.46
    焦点
    -0.46
    LinkId
    -0.43
    setViewName
    -0.43
    texttt
    -0.42
    wx
    -0.42
    芦
    -0.41
    中海
    -0.41
    -------------</
    -0.41
    NID
    -0.41
    POSITIVE LOGITS
     Serving
    1.18
     Serve
    1.14
     serving
    1.12
     serve
    1.11
    Serving
    1.10
     SERV
    1.08
     Served
    1.06
     served
    1.03
    serve
    1.02
    serving
    1.01
    Activations Density 0.082%

    No Known Activations