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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12500
    Prev
    Next
    INDEX
    Explanations

    technical terms related to networking, particularly focusing on data transmission and device connections

    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
    227
    +0.20
    0.7%
    998
    +0.12
    0.4%
    1967
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.13
    1904
    +0.12
    0.09
    270
    +0.11
    0.08
    Negative Logits
    <bos>
    -0.82
     kram
    -0.78
     thut
    -0.73
     aen
    -0.73
     pama
    -0.71
     inder
    -0.70
     meis
    -0.69
     „,
    -0.69
     nece
    -0.69
     zyn
    -0.68
    POSITIVE LOGITS
     xmin
    0.64
     Operand
    0.60
     ndarray
    0.56
     minValue
    0.56
     Lexer
    0.55
     Stateful
    0.54
     clc
    0.54
     Addr
    0.52
    backtracking
    0.52
     Attr
    0.51
    Activations Density 2.392%

    No Known Activations