© 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. 2209
    Prev
    Next
    INDEX
    Explanations

    new information or updates in a narrative

    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
    1150
    +0.09
    0.3%
    368
    +0.09
    0.2%
    972
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.09
    0.04
    1056
    +0.09
    0.04
    30
    +0.07
    0.04
    Negative Logits
     mtb
    -0.67
    postolic
    -0.65
     gmbh
    -0.60
    —(
    -0.59
     invin
    -0.59
     impra
    -0.59
     fuj
    -0.59
     wikihow
    -0.59
     lamborghini
    -0.57
     getty
    -0.56
    POSITIVE LOGITS
     كومونز
    0.54
     zvuky
    0.52
    CloseOperation
    0.51
    messageInfo
    0.50
     sambal
    0.48
     AssemblyCompany
    0.47
    EndProject
    0.47
    TextFormField
    0.46
    utnant
    0.46
    cellation
    0.46
    Activations Density 0.242%

    No Known Activations