© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3707
    Prev
    Next
    INDEX
    Explanations

    references to various specific items or concepts, likely related to detailed information or reviews

    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
    1235
    +0.09
    0.3%
    270
    +0.08
    0.2%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.09
    0.05
    270
    +0.08
    0.07
    1235
    +0.08
    0.07
    Negative Logits
     vogli
    -0.63
     sappi
    -0.62
    Xoxo
    -0.61
     vuol
    -0.61
     shutterstock
    -0.57
     scopri
    -0.56
     ritard
    -0.56
     conç
    -0.56
     inol
    -0.55
     yeezy
    -0.55
    POSITIVE LOGITS
     themselves
    0.78
    themselves
    0.74
     חיצוניים
    0.69
    Jeografia
    0.57
     disambiguazione
    0.56
     dacht
    0.54
    Dichloropropene
    0.53
    astéro
    0.51
    enderror
    0.49
     betweenstory
    0.49
    Activations Density 0.697%

    No Known Activations