© 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. 7403
    Prev
    Next
    INDEX
    Explanations

    technical details about a specific cryptocurrency called DASH and its advantages

    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
    674
    +0.08
    0.2%
    513
    +0.07
    0.2%
    1996
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1996
    +0.08
    0.02
    288
    +0.07
    0.03
    147
    +0.06
    0.01
    Negative Logits
     reluct
    -2.04
     volunte
    -1.93
     inev
    -1.91
     encomp
    -1.90
     Intere
    -1.88
     increa
    -1.88
     disagre
    -1.88
     Juf
    -1.87
     fta
    -1.83
     Gorb
    -1.80
    POSITIVE LOGITS
     maintain
    0.74
     gleichzeitig
    0.69
     keep
    0.68
     still
    0.68
     enough
    0.67
     maintaining
    0.66
     ALSO
    0.66
     allow
    0.66
     simultaneously
    0.64
     keeping
    0.63
    Activations Density 0.348%

    No Known Activations