© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1550
    Prev
    Next
    INDEX
    Explanations

    references to media coverage and its impact on public perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.1%
    198
    +0.12
    0.5%
    1150
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.29
    0.05
    198
    +0.12
    0.07
    1948
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.58
    حياته
    -0.57
    YMS
    -0.53
    BeginInit
    -0.49
    MergeFrom
    -0.49
    FunctionFlags
    -0.48
     SIMBAD
    -0.48
    PyExc
    -0.47
    lateinit
    -0.47
    LayoutStyle
    -0.47
    POSITIVE LOGITS
     Palembang
    1.27
     Keny
    1.25
     Minang
    1.24
     Khart
    1.23
     Jambi
    1.18
     Muhamma
    1.17
     Juf
    1.16
     Joaqu
    1.10
     Medan
    1.10
     Banjar
    1.09
    Activations Density 0.881%

    No Known Activations