© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    terms related to blockchain technology and its applications

    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
    599
    +0.10
    0.3%
    764
    +0.10
    0.3%
    262
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1107
    +0.10
    0.02
    1901
    +0.10
    0.02
    106
    +0.09
    0.03
    Negative Logits
    ⓧ
    -0.75
     compréhen
    -0.72
     Oester
    -0.70
     Rine
    -0.70
     emphat
    -0.69
     Bartholo
    -0.67
     Juf
    -0.66
     Schrö
    -0.66
     McLaugh
    -0.66
     maneu
    -0.66
    POSITIVE LOGITS
     applications
    0.74
     Applications
    0.71
     uses
    0.69
    Applications
    0.69
     Uses
    0.69
     usos
    0.69
    用途
    0.68
    Uses
    0.67
     APPLICATIONS
    0.67
     purposes
    0.66
    Activations Density 0.525%

    No Known Activations