© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6960
    Prev
    Next
    INDEX
    Explanations

    technical specifications and descriptors of physical features or components

    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
    994
    +0.14
    0.5%
    599
    +0.13
    0.5%
    1224
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.06
    1036
    +0.13
    -0.00
    994
    +0.13
    0.02
    Negative Logits
     Савезне
    -0.69
    <bos>
    -0.69
    HostException
    -0.63
    JspWriter
    -0.60
    DebuggerNonUser
    -0.57
    /**
    -0.57
    GEBURTS
    -0.55
     ExecuteAsync
    -0.54
     насељу
    -0.54
     onBackPressed
    -0.54
    POSITIVE LOGITS
     wien
    1.29
     ?...
    1.20
     sii
    1.20
     effe
    1.18
     sofia
    1.16
     !...
    1.16
     unden
    1.16
     haup
    1.16
     embodi
    1.15
     wikihow
    1.14
    Activations Density 0.624%

    No Known Activations