© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    names of computer technologies or brands starting with 'Mac'

    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
    1331
    +0.15
    0.6%
    795
    +0.15
    0.6%
    521
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.15
    0.03
    795
    +0.15
    0.03
    521
    +0.14
    0.02
    Negative Logits
    Leod
    -0.69
    Dermott
    -0.66
    acakt
    -0.66
    Allister
    -0.61
    Grath
    -0.61
    acağı
    -0.60
    artney
    -0.56
    Cormack
    -0.55
     Wicidata
    -0.51
    Bardzo
    -0.50
    POSITIVE LOGITS
    Mac
    1.24
     Mac
    1.23
     mac
    1.16
    mac
    1.09
     MAC
    1.05
     Macs
    1.03
     Mémoires
    1.01
     makro
    1.01
    MAC
    1.01
     Maciej
    0.97
    Activations Density 0.063%

    No Known Activations